diff --git a/bigbang/analysis/entity_recognition.py b/bigbang/analysis/entity_recognition.py
new file mode 100644
index 0000000..c55ad7e
--- /dev/null
+++ b/bigbang/analysis/entity_recognition.py
@@ -0,0 +1,340 @@
+# import necessary packages
+from bigbang.archive import Archive
+from bigbang.archive import load as load_archive
+
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+from transformers import pipeline
+
+import spacy
+from spacy.tokens import Span, Doc
+from spacy.util import filter_spans
+
+import pandas as pd
+
+from typing import List, Dict
+from collections import defaultdict
+import re
+import contractions
+from email_reply_parser import EmailReplyParser
+
+
+class SpanVisualizer:
+ """
+ A class to visualize spans. Results are taken from the huggingface models.
+ Using spacy for span visualization
+ """
+
+ def __init__(self):
+ self.ents = []
+ self.entity_dict = {}
+ self.entity_type = defaultdict(list)
+ self.merged_tokens = None
+ self.merged_labels = None
+ self.maps = None
+
+ def get_list_per_type(self):
+ if self.entity_dict:
+ for ent, type in self.entity_dict.items():
+ self.entity_type[type].append(ent)
+
+ def merge_tokens(self, tokens: List):
+ """
+ A utility function to merge sub-tokenized tokens from huggingface results.
+ """
+ merged_tokens = []
+ # this dictionary is used to store the mapping between the old index with the new merged index
+ maps = {}
+ merged_token = ""
+ for i, token in enumerate(tokens):
+ if not merged_token and token.startswith("##"):
+ merged_token = merged_tokens.pop()
+ merged_token += token[2:]
+ maps[i] = len(merged_tokens)
+ elif merged_token != "" and token.startswith("##"):
+ merged_token += token[2:]
+ maps[i] = len(merged_tokens)
+
+ if merged_token == "":
+ merged_tokens.append(token)
+ maps[i] = len(merged_tokens) - 1
+ else:
+ if (i == (len(tokens) - 1)) or (
+ i != len(tokens) - 1 and (not tokens[i + 1].startswith("##"))
+ ):
+ merged_tokens.append(merged_token)
+ merged_token = ""
+ self.merged_tokens = merged_tokens
+ self.maps = maps
+ return merged_tokens
+
+ def get_type(self, label: Dict):
+ return label["entity"].split("-")[-1]
+
+ def get_map_index(self, label: Dict, maps: Dict):
+ # get the mapped index from the merged tokens
+ return maps[label["index"] - 1]
+
+ def is_same(self, label: Dict, p_label: Dict, maps: Dict):
+ return (self.get_type(label) == self.get_type(p_label)) and (
+ self.get_map_index(label, maps) - self.get_map_index(p_label, maps) <= 1
+ )
+
+ def merge_labels(self, labels: List, maps: Dict):
+ # we merge the tokens that are consecutive with the same type as one entity mention
+ merged_labels = []
+ stack = []
+ # if the stack is empty we push the new label to the stack, else:
+ # check if the label is within the same entity mention, if it is, we push into the stack, else:
+ # we merge all the labels in the stack and pop it to the merged labels
+ for i, label in enumerate(labels):
+ if stack:
+ prev_label = stack[-1]
+ if self.is_same(label, prev_label, maps):
+ stack.append(label)
+ else:
+ merged_labels.append(stack)
+ stack = [label]
+ else:
+ stack.append(label)
+ if stack:
+ merged_labels.append(stack)
+ self.merged_labels = merged_labels
+ return merged_labels
+
+ def find_all_cap_ents(self, body: str, merged_tokens: list, doc: Doc):
+ # currently only supports single token all_cap words
+ # match all_cap words and find their positions
+ pattern = "[A-Z]+[A-Z]+[A-Z]*[\s]+"
+ all_caps = re.findall(pattern, body)
+ all_caps = [s.strip() for s in all_caps]
+ # find the words in the tokens
+ indexes = []
+ for word in all_caps:
+ for i, t in enumerate(merged_tokens):
+ if t == word:
+ if i not in indexes:
+ indexes.append(i)
+ break
+ # curating identified indexes list
+ rec_positions = []
+ for ent in self.ents:
+ for pos in range(ent.start, ent.end + 1):
+ rec_positions.append(pos)
+ # if not, adding to the entity list
+ entity_type = "ALLCAPS"
+ all_cap_ents = []
+ for start in indexes:
+ if start not in rec_positions:
+ end = start + 1
+ ent = Span(doc, start, end, entity_type)
+ # TODO: includnig differnet entities with the same names
+ self.entity_dict[str(ent)] = entity_type
+ all_cap_ents.append(ent)
+ self.ents.extend(all_cap_ents)
+ # for ent in self.ents:
+ # print(ent.start)
+ # print(self.ents)
+ doc.set_ents(self.ents)
+ return doc
+
+ def get_doc_for_visualization(
+ self,
+ tokens: List,
+ labels: list,
+ body: str,
+ doc: Doc,
+ find_all_caps: bool = True,
+ ):
+ if not self.merged_tokens or self.maps:
+ _ = self.merge_tokens(tokens)
+ if not self.merged_labels:
+ _ = self.merge_labels(labels, self.maps)
+
+ ents = []
+ starts = []
+
+ for m_labels in self.merged_labels:
+ start = self.get_map_index(m_labels[0], self.maps)
+ end = self.get_map_index(m_labels[-1], self.maps) + 1
+ entity_type = self.get_type(m_labels[0])
+ if start not in starts:
+ ent = Span(doc, start, end, entity_type)
+ self.entity_dict[str(ent)] = entity_type
+ ents.append(ent)
+ starts.append(start)
+ self.ents.extend(ents)
+ self.ents = filter_spans(self.ents)
+ doc.set_ents(self.ents)
+ if find_all_caps:
+ doc = self.find_all_cap_ents(body, self.merged_tokens, doc)
+ return doc
+
+
+class EntityRecognizer:
+ def __init__(self, model_name: str = "dslim/bert-base-NER"):
+ self.entities = []
+ self.model_name = model_name
+
+ self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
+ self.model = AutoModelForTokenClassification.from_pretrained(self.model_name)
+ self.nlp = pipeline("ner", model=self.model, tokenizer=self.tokenizer)
+
+ def remove_ori_message(self, body: str):
+ """
+ A function to remove the original message using package parsing
+ """
+ body = EmailReplyParser.parse_reply(body)
+ return body
+
+ def pre_processing(self, body: str, lowercase: bool = False):
+ """
+ A function to pre-process the email bodies. Including:
+ - expand contractions
+ - remove punctuations
+ - remove links
+ - remove all digits
+ - remove extra spaces and newlines
+ """
+ # parse reply
+ body = self.remove_ori_message(body)
+ # expand contractions
+ body = contractions.fix(body)
+ # # remove punctuations
+ # body = re.sub(r'[^\w\s]', '', body)
+ # remove links
+ body = re.sub(r"http\S+", "", body)
+ # remove all digits
+ body = re.sub(r"\d+", "", body)
+ # remove extra spaces and newlines
+ body = body.strip()
+ body = body.replace("\n", " ")
+ body = body.replace("\t", " ")
+ if lowercase:
+ body = body.lower()
+ return body
+
+ def recognize(self, data: str):
+ """
+ A wrapper for huggingface NER models.
+ """
+ return self.nlp(data)
+
+ def get_entities(self, tags: List):
+ """
+ A function process results from huggingface models and
+ get only the mentions and corresponding entity types
+ """
+ entities = []
+ for tag in tags:
+ name_type = {}
+ name_type["entity"] = tag["entity"]
+ name_type["word"] = tag["word"]
+ entities.append(name_type)
+ self.entities = entities
+ return entities
+
+
+pronouns = [
+ "i",
+ "you",
+ "me",
+ "my",
+ "mine",
+ "myself",
+ "your",
+ "yours",
+ "yourself",
+ "we",
+ "us",
+ "our",
+ "ours",
+ "ourselves",
+ "yourselves",
+ "he",
+ "him",
+ "himself",
+ "his",
+ "she",
+ "her",
+ "hers",
+ "herself",
+ "it",
+ "its",
+ "itself",
+ "they",
+ "them",
+ "their",
+ "theirs",
+ "themself",
+ "themselves",
+ "this",
+ "that",
+ "something",
+ "these",
+ "those",
+ "someone",
+ "somebody",
+ "who",
+ "whom",
+ "whose",
+ "which",
+ "what",
+]
+
+
+def process_list_entities(mailing_list="scipy-dev"):
+ mailing_list = "../../archives/scipy-dev/"
+
+ archive = Archive(mailing_list, mbox=True)
+ # archive data in pandas dataframe format
+ archive_data = archive.data
+ # taking a list of indexes as examples
+ num_data = len(archive_data)
+ num_data = 10
+ print("Process {} emails in total".format(num_data))
+ indexes = list(range(0, num_data))
+ lowercase = False
+ find_all_caps = True
+
+ model_name = "EffyLi/bert-base-NER-finetuned-ner-cerec"
+ # model_name = "dslim/bert-base-NER"
+ recognizer = EntityRecognizer(model_name)
+
+ nlp = spacy.load("en_core_web_sm")
+ vocab = nlp.tokenizer.vocab
+ save_file_name = mailing_list.split("/")[-2] + "-entities.csv"
+ columns_names = ["email_id", "entity", "type"]
+ df = pd.DataFrame(columns=columns_names)
+
+ email_entity_types = defaultdict(list)
+
+ # print('Process emails with id: ', indexes)
+ for index in indexes:
+ if index % 200 == 0:
+ print(
+ "{} emails processed, {} emails left.".format(index, (num_data - index))
+ )
+ body = list(archive_data["Body"].iloc[[index]])[0]
+ body = recognizer.pre_processing(body, lowercase=lowercase)
+
+ visualizer = SpanVisualizer()
+ # get labels from recognizer first
+ tokens = recognizer.tokenizer.tokenize(body)
+ labels = recognizer.recognize(body)
+ # merge tokens and spans in visualizer
+ merged_tokens = visualizer.merge_tokens(tokens)
+ doc = Doc(vocab=vocab, words=merged_tokens)
+ doc = visualizer.get_doc_for_visualization(
+ tokens, labels, body, doc, find_all_caps
+ )
+ visualizer.get_list_per_type()
+ entity_type = visualizer.entity_type
+ for k, v in entity_type.items():
+ email_entity_types[k].extend(v)
+ for v_i in v:
+ # remove pronouns
+ if v_i.lower() not in pronouns:
+ new_row = {"email_id": index, "entity": v_i, "type": k}
+ df = pd.concat([df, pd.DataFrame([new_row])], ignore_index=True)
+ df.to_csv(save_file_name)
+ print("Extracted entities saved!")
diff --git a/examples/llm_analysis/EmailBodyEntityAnalysis.ipynb b/examples/llm_analysis/EmailBodyEntityAnalysis.ipynb
new file mode 100644
index 0000000..a452eaf
--- /dev/null
+++ b/examples/llm_analysis/EmailBodyEntityAnalysis.ipynb
@@ -0,0 +1,1035 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "de89e4f9",
+ "metadata": {},
+ "source": [
+ "# Email body content analysis \n",
+ "\n",
+ "*For the context:* Current analysis in bigbang focus on headers. There are many analysis on the headers in the emails for the people and orgnization involved in the discussions. There are a few content analysis focusing on the keywords first occurence searching and/or most used words per user.\n",
+ "\n",
+ "This notebook analyze the email body contents with Huggingface Named Entity Recognition(NER) models that are able to systematically label the entities and their types(currently supports PER, ORG, LOC, and MISC) in the email bodies. This can potentially help the researchers understand more on the email conversations."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "8aadfe5c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# import necessary packages\n",
+ "from bigbang.archive import Archive\n",
+ "from bigbang.archive import load as load_archive\n",
+ "import pandas as pd\n",
+ "\n",
+ "# hide warnings\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "15b5230a",
+ "metadata": {},
+ "source": [
+ "First, use the script ```bin/collect_mail.py``` to collect web archives. Details can be seen in https://bigbang-py.readthedocs.io/en/latest/data-sources.html#id1 .\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "5d286f52",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "mailing_list = \"scipy-dev\"\n",
+ "archive_path = \"../../archives/{}/\".format(mailing_list)\n",
+ "archive = Archive(archive_path,mbox=True)\n",
+ "# archive data in pandas dataframe format\n",
+ "archive_data = archive.data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "a767ecdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "24953\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " From | \n",
+ " Subject | \n",
+ " Date | \n",
+ " In-Reply-To | \n",
+ " References | \n",
+ " Body | \n",
+ "
\n",
+ " \n",
+ " Message-ID | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " <NEBBIECAMLMAAKHEGPCGKEBHCLAA.travis@vaught.net> | \n",
+ " travis at vaught.net (Travis N. Vaught) | \n",
+ " [SciPy-dev] SciPy Developer mailing list now o... | \n",
+ " 2001-06-11 02:10:51+00:00 | \n",
+ " None | \n",
+ " None | \n",
+ " The link:\\n\\nhttp://scipy.net/mailman/listinfo... | \n",
+ "
\n",
+ " \n",
+ " <Pine.LNX.4.33.0107231957590.15960-100000@oliphant.ee.byu.edu> | \n",
+ " oliphant at ee.byu.edu (Travis Oliphant) | \n",
+ " [SciPy-dev] RPMs and source distribution | \n",
+ " 2001-07-24 02:01:00+00:00 | \n",
+ " <02f001c111bf$2e78a9d0$777ba8c0@190xb01> | \n",
+ " None | \n",
+ " I've been playing for hours and finally have i... | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
"
+ ],
+ "text/plain": [
+ " From \n",
+ "Message-ID \n",
+ " travis at vaught.net (Travis N. Vaught) \\\n",
+ " [SciPy-dev] SciPy Developer mailing list now o... \\\n",
+ " 2001-06-11 02:10:51+00:00 \\\n",
+ " None \\\n",
+ " \n",
+ "\n",
+ " References \n",
+ "Message-ID \n",
+ " None \\\n",
+ " The link:\\n\\nhttp://scipy.net/mailman/listinfo... \n",
+ "All , As \n",
+ "\n",
+ " I\n",
+ " PER\n",
+ "\n",
+ " mentioned in my previous message , \n",
+ "\n",
+ " I\n",
+ " PER\n",
+ "\n",
+ " have been trying to patch \n",
+ "\n",
+ " Fortran\n",
+ " ORG\n",
+ "\n",
+ " compilation to support fc . Unfortunately , after some work on patching both \n",
+ "\n",
+ " build\n",
+ " PER\n",
+ "\n",
+ " _ \n",
+ "\n",
+ " flib\n",
+ " PER\n",
+ "\n",
+ " . \n",
+ "\n",
+ " py\n",
+ " PER\n",
+ "\n",
+ " and the fc fc script , \n",
+ "\n",
+ " I\n",
+ " PER\n",
+ "\n",
+ " ran into several problems . . \n",
+ "\n",
+ " fc\n",
+ " PER\n",
+ "\n",
+ " puts the files into the current directory . . The build process runs into problems with the space in the platform name which contains " \n",
+ "\n",
+ " Power Macintosh\n",
+ " MISC\n",
+ "\n",
+ " " . In particular , \n",
+ "\n",
+ " ar\n",
+ " PER\n",
+ "\n",
+ " has problems with the space . I think , \n",
+ "\n",
+ " I\n",
+ " PER\n",
+ "\n",
+ " will wait until gcc . on \n",
+ "\n",
+ " OS\n",
+ " ALLCAPS\n",
+ "\n",
+ " X . That will have g support . Cheers , \n",
+ "\n",
+ " Tim Lahey\n",
+ " PER\n",
+ "\n",
+ "
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import spacy\n",
+ "from spacy import displacy\n",
+ "from spacy.tokens import Span, Doc\n",
+ "\n",
+ "# # defining a score threshold on the recognized entities. only entity has scored above the threshold will show\n",
+ "# threashold = 0.0\n",
+ "find_all_caps = True\n",
+ "\n",
+ "nlp = spacy.load(\"en_core_web_sm\")\n",
+ "vocab = nlp.tokenizer.vocab\n",
+ "\n",
+ "visualizer = SpanVisualizer()\n",
+ "merged_tokens = visualizer.merge_tokens(tokens)\n",
+ "doc = Doc(vocab=vocab, words=merged_tokens)\n",
+ "doc = visualizer.get_doc_for_visualization(tokens, labels, body, doc, find_all_caps)\n",
+ "\n",
+ "\n",
+ "displacy.render(doc, style='ent', jupyter=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "c23c2108",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "entity type: PER\n",
+ "\t- I\n",
+ "\t- build\n",
+ "\t- flib\n",
+ "\t- py\n",
+ "\t- fc\n",
+ "\t- ar\n",
+ "\t- Tim Lahey\n",
+ "entity type: ORG\n",
+ "\t- Fortran\n",
+ "entity type: MISC\n",
+ "\t- Power Macintosh\n",
+ "entity type: ALLCAPS\n",
+ "\t- OS\n"
+ ]
+ }
+ ],
+ "source": [
+ "visualizer.get_list_per_type()\n",
+ "entity_type_list = visualizer.entity_type\n",
+ "for typ, ent_list in entity_type_list.items():\n",
+ " print(\"entity type: \", typ)\n",
+ " for ent in ent_list:\n",
+ " print(\"\\t-\", ent)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "5a78f5a1",
+ "metadata": {},
+ "source": [
+ "## Processing the whole mailing list\n",
+ "\n",
+ "In the end, we show one example of how to pass a list of emails and return a list of entities with types. We save them in a csv file for futher processing."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "90c99e33",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "stop_words = ['i', 'you', 'me', 'my', 'mine', 'myself', 'your', 'yours',\n",
+ " 'yourself', 'we', 'us', 'our', 'ours', 'ourselves', 'yourselves',\n",
+ " 'he', 'him', 'himself', 'his', 'she', 'her', 'hers', 'herself', 'it', 'its', 'itself',\n",
+ " 'they', 'them', 'their', 'theirs', 'themself', 'themselves', 'this', 'that', 'something',\n",
+ " 'these', 'those', 'someone', 'somebody', 'who', 'whom', 'whose', 'which', 'what']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "168ef5ee",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Process 50 emails in total\n",
+ "0 emails processed, 50 emails left.\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Token indices sequence length is longer than the specified maximum sequence length for this model (1208 > 512). Running this sequence through the model will result in indexing errors\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Extracted entities saved!\n",
+ "entity type: PER\n",
+ "\t- you\n",
+ "\t- scipy - dev\n",
+ "\t- scipy . net\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- py\n",
+ "\t- I\n",
+ "\t- Travis\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- SciPy\n",
+ "\t- my\n",
+ "\t- flib\n",
+ "\t- py\n",
+ "\t- Cephes\n",
+ "\t- Tim Lahey\n",
+ "\t- I\n",
+ "\t- build\n",
+ "\t- flib\n",
+ "\t- py\n",
+ "\t- fc\n",
+ "\t- ar\n",
+ "\t- Tim Lahey\n",
+ "\t- I\n",
+ "\t- us\n",
+ "\t- de Boor\n",
+ "\t- Tim Lahey\n",
+ "\t- Tim\n",
+ "\t- I\n",
+ "\t- Travis Oliphant\n",
+ "\t- he\n",
+ "\t- you\n",
+ "\t- Travis O .\n",
+ "\t- I\n",
+ "\t- your\n",
+ "\t- I\n",
+ "\t- splines\n",
+ "\t- I\n",
+ "\t- Carl de Boor\n",
+ "\t- Joe\n",
+ "\t- You\n",
+ "\t- you\n",
+ "\t- me\n",
+ "\t- your\n",
+ "\t- We\n",
+ "\t- your member\n",
+ "\t- I\n",
+ "\t- everyone\n",
+ "\t- eric\n",
+ "\t- I\n",
+ "\t- me\n",
+ "\t- Joe rossini\n",
+ "\t- you\n",
+ "\t- washington . edu\n",
+ "\t- A . J . Rossini\n",
+ "\t- I\n",
+ "\t- anyone\n",
+ "\t- us\n",
+ "\t- you\n",
+ "\t- Travis Vaught\n",
+ "\t- I\n",
+ "\t- rossini\n",
+ "\t- A . J . Rossini\n",
+ "\t- I\n",
+ "\t- me\n",
+ "\t- you\n",
+ "\t- JMR\n",
+ "\t- I\n",
+ "\t- Eric\n",
+ "\t- he\n",
+ "\t- Numpy\n",
+ "\t- I\n",
+ "\t- Rob\n",
+ "\t- ps\n",
+ "\t- my Fortran\n",
+ "\t- I\n",
+ "\t- linalg\n",
+ "\t- Travis O .\n",
+ "\t- we\n",
+ "\t- you\n",
+ "\t- lapack\n",
+ "\t- pyf\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- cygwin\n",
+ "\t- fpy\n",
+ "\t- me\n",
+ "\t- Pearu\n",
+ "\t- I\n",
+ "\t- Pearu\n",
+ "\t- I\n",
+ "\t- me\n",
+ "\t- Jochen\n",
+ "\t- Jason\n",
+ "\t- I\n",
+ "\t- me\n",
+ "\t- Cygwin\n",
+ "\t- Jason\n",
+ "\t- Travis\n",
+ "\t- cygwin\n",
+ "\t- Pearu\n",
+ "\t- Jochen\n",
+ "\t- you\n",
+ "\t- my\n",
+ "\t- I\n",
+ "\t- libpython\n",
+ "\t- dll\n",
+ "\t- You\n",
+ "\t- distutils\n",
+ "\t- sig\n",
+ "\t- python . org\n",
+ "\t- Jason\n",
+ "\t- I\n",
+ "\t- my\n",
+ "\t- Pearu\n",
+ "\t- I\n",
+ "\t- you\n",
+ "\t- ravel\n",
+ "\t- Matlab\n",
+ "\t- Zope\n",
+ "\t- you\n",
+ "\t- I\n",
+ "\t- I\n",
+ "\t- William\n",
+ "\t- everyone\n",
+ "\t- My\n",
+ "\t- plt\n",
+ "\t- You\n",
+ "\t- I\n",
+ "\t- PythonCard\n",
+ "\t- PyCrust\n",
+ "\t- she\n",
+ "\t- I\n",
+ "\t- they\n",
+ "\t- PowerPoint\n",
+ "\t- my\n",
+ "\t- Kevin Altis altis\n",
+ "\t- semi\n",
+ "\t- retired . com\n",
+ "\t- I\n",
+ "\t- Jochen\n",
+ "\t- Einigkeit\n",
+ "\t- SunOS\n",
+ "\t- I\n",
+ "\t- Jochen\n",
+ "\t- you\n",
+ "\t- your\n",
+ "\t- pyCrust\n",
+ "\t- wxPython\n",
+ "\t- gui _ thread\n",
+ "\t- Python\n",
+ "\t- plt\n",
+ "\t- py\n",
+ "\t- I\n",
+ "\t- wxGTK\n",
+ "\t- I\n",
+ "\t- me\n",
+ "\t- eric\n",
+ "\t- Sun\n",
+ "\t- I\n",
+ "\t- you\n",
+ "\t- your\n",
+ "\t- me\n",
+ "\t- SciPy\n",
+ "\t- build\n",
+ "\t- flib . py\n",
+ "\t- eric\n",
+ "\t- I\n",
+ "\t- f\n",
+ "\t- dryrun\n",
+ "\t- eric\n",
+ "\t- BEGIN\n",
+ "\t- I\n",
+ "\t- plt\n",
+ "\t- you\n",
+ "\t- py\n",
+ "\t- my\n",
+ "\t- gui\n",
+ "\t- plot . py\n",
+ "\t- kplot . py\n",
+ "\t- Greetings , Jochen\n",
+ "\t- Venable Hall\n",
+ "\t- #\n",
+ "\t- Kenan C\n",
+ "\t- Hill\n",
+ "entity type: DIG\n",
+ "\t- list\n",
+ "\t- representation\n",
+ "\t- Guide\n",
+ "\t- Mathematics\n",
+ "\t- org\n",
+ "\t- THREADS\n",
+ "\t- THEM Project www . members . home . net / europax\n",
+ "\t- directory\n",
+ "\t- _\n",
+ "\t- document\n",
+ "\t- jkext\n",
+ "entity type: ORG\n",
+ "\t- our\n",
+ "\t- they\n",
+ "\t- Distutils\n",
+ "\t- PyOpenGL\n",
+ "\t- Fortran\n",
+ "\t- SciPy\n",
+ "\t- CVS\n",
+ "\t- SLATEC\n",
+ "\t- Netlib\n",
+ "\t- SLATEC\n",
+ "\t- we\n",
+ "\t- SciPy\n",
+ "\t- we\n",
+ "\t- SciPy\n",
+ "\t- they\n",
+ "\t- SLATEC\n",
+ "\t- spline\n",
+ "\t- Springer - Verlag\n",
+ "\t- we\n",
+ "\t- scipy . org\n",
+ "\t- scipy\n",
+ "\t- .\n",
+ "\t- our\n",
+ "\t- edu\n",
+ "\t- We\n",
+ "\t- We\n",
+ "\t- we\n",
+ "\t- We\n",
+ "\t- we\n",
+ "\t- blindglobe\n",
+ "\t- FORTRAN\n",
+ "\t- USENET\n",
+ "\t- ATLAS\n",
+ "\t- FreeBSD\n",
+ "\t- ATLAS\n",
+ "\t- ATLAS\n",
+ "\t- CYGWIN\n",
+ "\t- CYGWIN\n",
+ "\t- Cygwin\n",
+ "\t- Modules\n",
+ "\t- Distutils\n",
+ "\t- NumPy\n",
+ "\t- NumPy\n",
+ "\t- Matlab\n",
+ "\t- AppleEvents\n",
+ "\t- Excel\n",
+ "\t- SciPy\n",
+ "\t- PythonCard\n",
+ "\t- University of North Carolina\n",
+ "\t- Department of Chemistry\n",
+ "\t- und Recht\n",
+ "\t- Freiheit\n",
+ "\t- Fortran\n",
+ "\t- PlotCanvas\n",
+ "\t- scipy\n",
+ "\t- University of North Carolina\n",
+ "\t- Department of Chemistry\n",
+ "\t- NC\n",
+ "\t- BCCDE\n",
+ "entity type: MISC\n",
+ "\t- Mac OS X\n",
+ "\t- Power Macintosh\n",
+ "\t- Python\n",
+ "\t- Windows\n",
+ "\t- Debian\n",
+ "\t- C\n",
+ "\t- Windows\n",
+ "\t- Python\n",
+ "\t- Cygwin Python\n",
+ "\t- Calcusyn\n",
+ "\t- Python\n",
+ "entity type: ALLCAPS\n",
+ "\t- OS\n",
+ "\t- GIST\n",
+ "\t- OS\n",
+ "\t- OS\n",
+ "\t- BSPEV\n",
+ "\t- BSPVD\n",
+ "\t- BSPPP\n",
+ "\t- BINTK\n",
+ "\t- BINT\n",
+ "\t- BSQAD\n",
+ "\t- PPQAD\n",
+ "\t- BFQAD\n",
+ "\t- PFQAD\n",
+ "\t- BVALU\n",
+ "\t- PPVAL\n",
+ "\t- INTRV\n",
+ "\t- BSPDR\n",
+ "\t- BSPVN\n",
+ "\t- FEM\n",
+ "\t- RH\n",
+ "\t- AIX\n",
+ "\t- LAPACK\n",
+ "\t- SAVE\n",
+ "\t- LAPACK\n",
+ "\t- LAPACK\n",
+ "\t- GCC\n",
+ "\t- RCS\n",
+ "\t- NC\n",
+ "\t- USA\n",
+ "\t- EXPORT\n",
+ "\t- EXPORT\n",
+ "\t- BCCDE\n",
+ "\t- URL\n",
+ "\t- EXPORT\n",
+ "\t- IMPORT\n",
+ "\t- PM\n",
+ "\t- PDF\n",
+ "\t- COM\n",
+ "\t- PGP\n",
+ "\t- BEGIN\n",
+ "\t- SHA\n",
+ "\t- BCCDE\n",
+ "\t- END\n",
+ "\t- BEGIN\n",
+ "\t- PGP\n",
+ "\t- SIGNED\n",
+ "\t- SHA\n",
+ "\t- RCS\n",
+ "\t- BCCDE\n",
+ "\t- END\n",
+ "\t- SUN\n",
+ "\t- GTK\n",
+ "\t- DISPLAY\n",
+ "\t- SIGNED\n",
+ "\t- RCS\n",
+ "\t- PNG\n",
+ "\t- BMP\n",
+ "\t- JPEG\n",
+ "\t- PCX\n",
+ "\t- TIFF\n",
+ "\t- BCCDE\n",
+ "\t- RCS\n",
+ "\t- USA\n",
+ "entity type: LOC\n",
+ "\t- New York ,\n",
+ "\t- SciPy site\n",
+ "\t- SciPy\n",
+ "\t- Chapel Hill , NC\n",
+ "\t- USA\n"
+ ]
+ }
+ ],
+ "source": [
+ "from collections import defaultdict\n",
+ "\n",
+ "# taking a list of indexes as examples\n",
+ "num_data = len(archive_data)\n",
+ "num_data = 50\n",
+ "print(\"Process {} emails in total\".format(num_data))\n",
+ "indexes = list(range(0, num_data))\n",
+ "lowercase = False\n",
+ "find_all_caps = True\n",
+ "\n",
+ "model_name = \"EffyLi/bert-base-NER-finetuned-ner-cerec\"\n",
+ "# model_name = \"dslim/bert-base-NER\"\n",
+ "recognizer = EntityRecognizer(model_name)\n",
+ "\n",
+ "nlp = spacy.load(\"en_core_web_sm\")\n",
+ "vocab = nlp.tokenizer.vocab\n",
+ "save_file_path = \"../../archives/\"\n",
+ "save_file_name = archive_path.split(\"/\")[-2] + '-entities.csv'\n",
+ "columns_names = ['email_id', 'entity', 'type']\n",
+ "df = pd.DataFrame(columns=columns_names)\n",
+ "\n",
+ "email_entity_types = defaultdict(list)\n",
+ "\n",
+ "# print('Process emails with id: ', indexes)\n",
+ "for index in indexes:\n",
+ " if index % 200 == 0:\n",
+ " print(\"{} emails processed, {} emails left.\".format(index, (num_data-index)))\n",
+ " body = list(archive_data['Body'].iloc[[index]])[0]\n",
+ " body = recognizer.pre_processing(body, lowercase=lowercase)\n",
+ "# show email bodies after pre-processing\n",
+ "# print(body)\n",
+ "\n",
+ " visualizer = SpanVisualizer()\n",
+ " # get labels from recognizer first\n",
+ " tokens = recognizer.tokenizer.tokenize(body) \n",
+ " labels = recognizer.recognize(body)\n",
+ " # merge tokens and spans in visualizer\n",
+ " merged_tokens = visualizer.merge_tokens(tokens)\n",
+ " doc = Doc(vocab=vocab, words=merged_tokens)\n",
+ " doc = visualizer.get_doc_for_visualization(tokens, labels, body, doc, find_all_caps)\n",
+ " visualizer.get_list_per_type()\n",
+ " entity_type = visualizer.entity_type\n",
+ " for k, v in entity_type.items():\n",
+ " email_entity_types[k].extend(v)\n",
+ " for v_i in v:\n",
+ " # remove pronouns\n",
+ " if v_i.lower() not in stop_words:\n",
+ " new_row = {\"email_id\": index, \"entity\": v_i, \"type\": k}\n",
+ " df = pd.concat([df, pd.DataFrame([new_row])], ignore_index=True)\n",
+ "df.to_csv(save_file_name)\n",
+ "print(\"Extracted entities saved!\")\n",
+ "\n",
+ "for typ, ent_list in email_entity_types.items():\n",
+ " print(\"entity type: \", typ)\n",
+ " for ent in ent_list:\n",
+ " print(\"\\t-\", ent) "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "e13e1de8",
+ "metadata": {},
+ "source": [
+ "## Run the cell below only to display pre-processed mailing list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "901dd616",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "# load pre-processed csv file to dataframe and display\n",
+ "file_path = 'extracted_entities/3gv6-entities.csv'\n",
+ "df = pd.read_csv(file_path)\n",
+ "\n",
+ "# get top 10 frequent entities for each category\n",
+ "categories = list(set(recognizer.model.config.id2label.values()))\n",
+ "categories = list(set([c.split('-')[-1] if '-' in c else c for c in categories ]))\n",
+ "\n",
+ "for c in categories:\n",
+ " if c != \"O\":\n",
+ " if c ==\"PER\":\n",
+ " print(\"Top 10 occurence (pronouns excluded) for type: \", c)\n",
+ " else:\n",
+ " print(\"Top 10 occurence for type: \", c)\n",
+ " df_c = df.loc[df['type'] == c]\n",
+ " display_df = df_c['entity'].value_counts().rename_axis('entity').reset_index(name='counts')\n",
+ " display(display_df.head(10))\n",
+ " print()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "555e1ba7",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "bigbang2",
+ "language": "python",
+ "name": "bigbang2"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.16"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/examples/llm_analysis/extracted_entities/3gv6-entities.csv b/examples/llm_analysis/extracted_entities/3gv6-entities.csv
new file mode 100644
index 0000000..1095f8d
--- /dev/null
+++ b/examples/llm_analysis/extracted_entities/3gv6-entities.csv
@@ -0,0 +1,2316 @@
+,email_id,entity,type
+0,0,Basavaraj Patil,PER
+1,1,ML,ORG
+2,1,Shanghai,LOC
+3,1,GPP,ALLCAPS
+4,2,des,PER
+5,3,Raj,PER
+6,4,Discuss Jari BasavarajPatilnokiacom,PER
+7,5,Basavaraj Patil,PER
+8,6,Raj,PER
+9,7,Alan I,PER
+10,7,Hui rahulvsamsungcom,PER
+11,7,rahulvsamsungcom,ORG
+12,7,suntaochinamobilecom,ORG
+13,7,PDN,ORG
+14,7,APN,ORG
+15,8,Thanks Hui,PER
+16,8,people,PER
+17,8,Best,PER
+18,8,IPv,ORG
+19,9,ZTE,ORG
+20,10,Jari,PER
+21,11,Jari,PER
+22,12,China Mobile Workshop,ORG
+23,12,Basavaraj Patil Nokia,PER
+24,12,David Crowe,PER
+25,12,DSMIP,ALLCAPS
+26,12,IP,ALLCAPS
+27,12,GPP,ALLCAPS
+28,13,David I,PER
+29,13,Yutaka,PER
+30,14,Ah,PER
+31,14,Jari David Crowe,PER
+32,15,IETF,ORG
+33,15,NAT,ALLCAPS
+34,16,Hi Charlie DS,PER
+35,16,DS,ORG
+36,17,CharlieAA I,PER
+37,17,DS,PER
+38,17,HuiAARe gardsAABehcetAAAA,PER
+39,17,Charles E Perkins charliepcomputerorgA,PER
+40,17,hostsA,ORG
+41,17,IETF,ORG
+42,17,ML,ALLCAPS
+43,17,PMA,ALLCAPS
+44,17,NATA,ALLCAPS
+45,17,PA,ALLCAPS
+46,18,Raj I,PER
+47,18,DS,ORG
+48,18,IPv,DIG
+49,19,Stefano,PER
+50,19,Basavaraj,PER
+51,19,IPv,DIG
+52,19,Dualstack,ORG
+53,20,IETF,ORG
+54,20,RFC,MISC
+55,20,Internet,MISC
+56,20,IVI,ALLCAPS
+57,21,RFC,PER
+58,21,Apple,ORG
+59,21,iPhone,ORG
+60,22,Stefano,PER
+61,22,GOING,ALLCAPS
+62,22,TO,ALLCAPS
+63,23,ipv,PER
+64,23,Ipv,ORG
+65,23,AAAA,ALLCAPS
+66,23,NAT,ALLCAPS
+67,24,Fred Baker fredciscoco mA,PER
+68,24,BasavarajPatilnokiacom BasavarajPatilnokiacomA,PER
+69,24,PMA,ORG
+70,24,Apple,ORG
+71,24,iPhone,ORG
+72,24,AAAA,ALLCAPS
+73,24,PM,ALLCAPS
+74,24,DS,ALLCAPS
+75,24,RFC,ALLCAPS
+76,25,Charles E,PER
+77,25,charliepcomputerorgA,PER
+78,25,ACrica,PER
+79,25,Jari,PER
+80,25,DualstackA,ORG
+81,25,payoffAAI,ORG
+82,25,Shanghai WorkshopAARegardsAABehcetAAA,ORG
+83,26,Frank You,PER
+84,26,Hui gerardogqualcommcom SebastianSpeichertmobilenet,PER
+85,26,IAPD,ORG
+86,26,RFC,ORG
+87,26,SebastianSpeichertmobilenet,ORG
+88,27,Hi Hui I,PER
+89,27,UEs,ORG
+90,27,Internet,ORG
+91,27,APN,ALLCAPS
+92,27,RFC,ALLCAPS
+93,28,Teemu,PER
+94,28,Franks,PER
+95,28,Hui,PER
+96,28,UE,ORG
+97,28,RSRA,ORG
+98,28,hongchengsgpanasoniccom,ORG
+99,29,Hi Hui,PER
+100,29,GPP,ALLCAPS
+101,29,UE,ALLCAPS
+102,29,PDP,ALLCAPS
+103,29,ISP,ALLCAPS
+104,29,RFC,ALLCAPS
+105,29,GW,ALLCAPS
+106,29,RD,ALLCAPS
+107,29,RA,ALLCAPS
+108,29,LAN,ORG
+109,29,UEs,ORG
+110,30,TeemuAA I,PER
+111,30,Nemo,PER
+112,30,NemoPD,PER
+113,30,WG,PER
+114,30,teemusavolainennokiac,PER
+115,30,teemusavolainennokiacomA,PER
+116,30,local,ORG
+117,30,PMA,ALLCAPS
+118,30,UE,ALLCAPS
+119,30,PD,ALLCAPS
+120,30,DHCP,ALLCAPS
+121,30,RFC,ALLCAPS
+122,30,BUBA,ALLCAPS
+123,30,RR,ALLCAPS
+124,30,HA,ALLCAPS
+125,30,MR,ALLCAPS
+126,30,AAAA,ALLCAPS
+127,30,GPP,ALLCAPS
+128,30,PDP,ALLCAPS
+129,30,LAN,ALLCAPS
+130,30,GW,ALLCAPS
+131,30,RD,ALLCAPS
+132,30,ISP,ALLCAPS
+133,30,RA,ALLCAPS
+134,30,DHC,ALLCAPS
+135,30,APN,ALLCAPS
+136,30,CPE,ALLCAPS
+137,30,DA,ALLCAPS
+138,30,RE,ALLCAPS
+139,30,UEA,ALLCAPS
+140,30,RSRAA,ALLCAPS
+141,30,RSRA,ALLCAPS
+142,30,AMA,ALLCAPS
+143,30,IAPD,ALLCAPS
+144,30,RFCA,ALLCAPS
+145,30,GMOBILECNA,ALLCAPS
+146,30,PDA,ALLCAPS
+147,30,DHCPA,ALLCAPS
+148,30,ECN,ALLCAPS
+149,30,YC,ALLCAPS
+150,30,NGMOBILECNA,ALLCAPS
+151,30,BENNETT,ALLCAPS
+152,30,PS,ALLCAPS
+153,30,SA,ALLCAPS
+154,31,Teemu You,PER
+155,31,EPC PDP,ORG
+156,31,UE RSRA,ORG
+157,31,DHCPv,DIG
+158,31,APN,ALLCAPS
+159,32,RFC,ORG
+160,32,farooqbariattcom nishidaknttdocomocojp xzhaorimcom,ORG
+161,32,denghuichinamobilecom,ORG
+162,32,Frank farooqbariattcom,PER
+163,32,xzhaorimcom,PER
+164,32,huaruiliangsamsungcom,PER
+165,32,FB,ALLCAPS
+166,34,PDP,ORG
+167,34,PDN,ORG
+168,34,UE,ORG
+169,34,RSRA,ORG
+170,34,SLAAC,ORG
+171,34,Network,ORG
+172,34,UEs,ORG
+173,34,PDN GW,ORG
+174,34,Internet,ORG
+175,34,GW wi,PER
+176,34,Teemu,PER
+177,34,ABBA,ALLCAPS
+178,34,ISP,ALLCAPS
+179,34,GW,ALLCAPS
+180,34,RS,ALLCAPS
+181,34,RA,ALLCAPS
+182,34,APN,ALLCAPS
+183,35,UE,ORG
+184,35,UEs,ORG
+185,35,ABBA,ALLCAPS
+186,35,ISP,ALLCAPS
+187,36,Behcet,PER
+188,36,Teemu,PER
+189,36,Nemo,ORG
+190,37,UE,ORG
+191,37,IANA,ORG
+192,37,GPP,ALLCAPS
+193,37,PCC,ALLCAPS
+194,37,RIR,ALLCAPS
+195,37,CPE,ALLCAPS
+196,38,Teemu,PER
+197,38,my side teemusavolainennokiacom,PER
+198,38,PDN GW,ORG
+199,38,SLAAC,ORG
+200,38,RSRA,ORG
+201,38,UE,ALLCAPS
+202,38,PDP,ALLCAPS
+203,38,EPS,ALLCAPS
+204,39,Julien,PER
+205,39,an UE,PER
+206,39,Teemu,PER
+207,39,UEs,ORG
+208,39,RFC,ALLCAPS
+209,39,APN,ALLCAPS
+210,39,LTE,ALLCAPS
+211,39,PD,ALLCAPS
+212,40,teemusavolainennokiacom,PER
+213,40,UE,ORG
+214,40,UEs,ORG
+215,40,RFC,ALLCAPS
+216,40,OTOH,ALLCAPS
+217,41,Teemu I,PER
+218,41,ur,PER
+219,41,Thanks Hui,PER
+220,41,APN,ORG
+221,41,PD,ORG
+222,41,PDP,ORG
+223,41,RSRA,ORG
+224,41,PDN,ORG
+225,43,Fredrik You,PER
+226,43,UE,ORG
+227,43,GW,ORG
+228,43,UEs,ORG
+229,43,RIRIANA,ORG
+230,43,RA,ALLCAPS
+231,44,UE,ORG
+232,44,RFC,ORG
+233,44,DHCPv,ORG
+234,44,Teemu,PER
+235,44,GW,ALLCAPS
+236,44,PD,ALLCAPS
+237,45,RD,ALLCAPS
+238,45,IPvonly,ORG
+239,45,UE,ORG
+240,46,Hi Hui,PER
+241,46,origi,PER
+242,46,PDN,ORG
+243,46,APN,ALLCAPS
+244,47,TeemuAA,PER
+245,47,Nemo I,PER
+246,47,dsAABehcetAAA,PER
+247,47,teemusavola inennokiacom teemusavolainennokiacomA,PER
+248,47,sarikayaieeeorg,PER
+249,47,ietforgA,PER
+250,47,Sarikaya,PER
+251,47,cetsarikayayahoocomA,PER
+252,47,Savolain en Teemu NokiaDMSWTampere gvietforgA,PER
+253,47,ce,ORG
+254,47,ISP,ALLCAPS
+255,47,AMA,ALLCAPS
+256,47,RE,ALLCAPS
+257,47,PDA,ALLCAPS
+258,47,WG,ALLCAPS
+259,47,DHCP,ALLCAPS
+260,47,PD,ALLCAPS
+261,47,RFCA,ALLCAPS
+262,47,BUBA,ALLCAPS
+263,47,RR,ALLCAPS
+264,47,HA,ALLCAPS
+265,47,MRA,ALLCAPS
+266,47,PMA,ALLCAPS
+267,47,RFC,ALLCAPS
+268,47,GPP,ALLCAPS
+269,47,UE,ALLCAPS
+270,47,PDPA,ALLCAPS
+271,47,AN,ALLCAPS
+272,47,PDP,ALLCAPS
+273,47,GW,ALLCAPS
+274,47,RD,ALLCAPS
+275,47,RA,ALLCAPS
+276,47,UEA,ALLCAPS
+277,47,APN,ALLCAPS
+278,47,APNA,ALLCAPS
+279,47,CPE,ALLCAPS
+280,47,DA,ALLCAPS
+281,47,RSRA,ALLCAPS
+282,47,IAPD,ALLCAPS
+283,47,SP,ALLCAPS
+284,47,DHCPA,ALLCAPS
+285,47,GPPA,ALLCAPS
+286,47,YC,ALLCAPS
+287,47,BENNETT,ALLCAPS
+288,48,France Telecom Group,ORG
+289,48,CPE,ALLCAPS
+290,49,Bechet I,PER
+291,49,CPE,ORG
+292,49,WLAN,ORG
+293,49,NA,ORG
+294,49,ND,ALLCAPS
+295,49,ISP,ALLCAPS
+296,49,RFC,ALLCAPS
+297,50,David,PER
+298,50,PD,ALLCAPS
+299,50,CPE,ALLCAPS
+300,51,Teemu,PER
+301,51,twork,PER
+302,51,the UE,ORG
+303,51,the network,ORG
+304,51,UE,ORG
+305,51,PDN,ORG
+306,51,Network,ORG
+307,51,GPP,ORG
+308,51,IETF,ORG
+309,51,RA,ALLCAPS
+310,51,PD,ALLCAPS
+311,52,Julien,PER
+312,52,t he operator,PER
+313,52,DHCPv,PER
+314,52,RFC,ALLCAPS
+315,52,IP,ALLCAPS
+316,52,RD,ALLCAPS
+317,53,Teemu,PER
+318,53,UE,ALLCAPS
+319,53,GPP,ALLCAPS
+320,53,PCC,ALLCAPS
+321,54,Fredrik,PER
+322,54,me Frank,PER
+323,54,PEs,PER
+324,54,Teemu,ORG
+325,54,ID,ALLCAPS
+326,55,Jari Arkko,PER
+327,56,Hi allAAAAJari,PER
+328,56,allAAAAJari,ORG
+329,56,GPP,ALLCAPS
+330,56,AAI,ALLCAPS
+331,57,teemusavolainennokiacom,PER
+332,57,yousavolainennokiacomA,PER
+333,57,sarikayaieeeorgA,PER
+334,57,gvbouncesietforg,PER
+335,57,OfA,PER
+336,57,SarikayaA,PER
+337,57,gvietforgA,PER
+338,57,A Jari Arkko,PER
+339,57,PDN,ORG
+340,57,AR,ORG
+341,57,DHCP,ALLCAPS
+342,57,UE,ALLCAPS
+343,57,AA,ALLCAPS
+344,57,PD,ALLCAPS
+345,57,SLAAC,ALLCAPS
+346,57,PMA,ALLCAPS
+347,57,RE,ALLCAPS
+348,57,EPS,ALLCAPS
+349,57,RFC,ALLCAPS
+350,57,GPP,ALLCAPS
+351,59,PDN,ORG
+352,59,UE,ORG
+353,59,GPP,ORG
+354,59,UEs,ORG
+355,59,Teemu,PER
+356,59,PD,ALLCAPS
+357,60,GPP,ORG
+358,60,UE,ORG
+359,60,AR,ORG
+360,60,SLAAC,ORG
+361,60,Jouni,PER
+362,60,teemusavolainennokiacom,PER
+363,60,PGW,ALLCAPS
+364,60,AAA,ALLCAPS
+365,60,RFC,ALLCAPS
+366,60,DHCP,ALLCAPS
+367,60,AM,ALLCAPS
+368,60,PDN,ALLCAPS
+369,60,GW,ALLCAPS
+370,61,IETF,ORG
+371,61,GPP,ORG
+372,61,IMHO,ORG
+373,61,PDN,ORG
+374,61,UE,ORG
+375,61,France Telecom Group,ORG
+376,61,DHPC,PER
+377,61,PCOIE,PER
+378,61,MN,ALLCAPS
+379,61,ETFGPP,ALLCAPS
+380,62,BEHAVE,PER
+381,62,UTRAN,ORG
+382,62,NAT,ALLCAPS
+383,62,DNS,ALLCAPS
+384,62,SAE,ALLCAPS
+385,63,Teemu I,PER
+386,63,ID,ALLCAPS
+387,64,UE AR,ORG
+388,64,Mext,ORG
+389,64,Network,ORG
+390,64,MR,ORG
+391,64,DHCP,ORG
+392,64,UE,ALLCAPS
+393,64,RR,ALLCAPS
+394,64,IP,ALLCAPS
+395,64,Teemu,PER
+396,64,WG,PER
+397,64,Nemo,PER
+398,65,David davidbinetorangeftgroupcom,PER
+399,65,GPP,ORG
+400,65,IETF,ORG
+401,65,UE,ORG
+402,65,SLAAC,ALLCAPS
+403,65,PCO,ALLCAPS
+404,65,IMHO,ALLCAPS
+405,66,Hello,ORG
+406,66,IMHO,ORG
+407,66,Teemu teemusavolainennokiacom,PER
+408,66,RD,ALLCAPS
+409,67,UE,ALLCAPS
+410,67,AR,ALLCAPS
+411,67,DHCP,ALLCAPS
+412,67,BINET,ALLCAPS
+413,67,NCPINADTIP,ALLCAPS
+414,67,RR,ALLCAPS
+415,67,WG,ALLCAPS
+416,67,MR,ALLCAPS
+417,67,PD,ALLCAPS
+418,67,IP,ALLCAPS
+419,67,UE AR,ORG
+420,67,sarikayaieeeorg,PER
+421,67,Teemu,PER
+422,68,Julien,PER
+423,68,David,PER
+424,68,De Laganier Julien julienlqualcommcom,PER
+425,68,David davidbinetorangeftgroupcom,PER
+426,68,GPP,ORG
+427,68,IETF,ORG
+428,68,UE,ORG
+429,68,teemusavolainennokiacom,DIG
+430,68,ND,ALLCAPS
+431,68,DHCP,ALLCAPS
+432,68,BINET,ALLCAPS
+433,68,NCPINADTIP,ALLCAPS
+434,68,RE,ALLCAPS
+435,68,SLAAC,ALLCAPS
+436,68,PCO,ALLCAPS
+437,68,IMHO,ALLCAPS
+438,69,UE,ORG
+439,69,IMHO,ORG
+440,69,GGSN,ORG
+441,69,PGW,DIG
+442,69,FWIW,ALLCAPS
+443,69,ND,ALLCAPS
+444,69,DHCP,ALLCAPS
+445,69,SLAAC,ALLCAPS
+446,69,PCO,ALLCAPS
+447,69,EPS,ALLCAPS
+448,69,PDP,ALLCAPS
+449,69,APN,ALLCAPS
+450,70,Cameron Byrne cblistgmailc,PER
+451,70,davidbinetorangeftgroupcomA,PER
+452,70,Laganier Julien,PER
+453,70,teemusavolainennokiacom teemusavolainennokiacom,PER
+454,70,AA,ALLCAPS
+455,70,PDP,ALLCAPS
+456,70,RFC,ALLCAPS
+457,70,AMA,ALLCAPS
+458,70,RE,ALLCAPS
+459,70,FWIW,ALLCAPS
+460,70,UE,ALLCAPS
+461,70,ND,ALLCAPS
+462,70,DHCP,ALLCAPS
+463,71,Alkuperinen,ORG
+464,71,Dec Lhettj,ORG
+465,71,Arkko jariarkkopiuhanet Vastaanottaja Internet Area intareaietforg CC Bertenyi Balazs NSN HUBudapest balazsbertenyinsncom Viittaukset BCpiuhanet We,ORG
+466,71,gppietf,PER
+467,71,Pivys Wed,PER
+468,71,Jari,PER
+469,73,IP,ALLCAPS
+470,73,DNS,ALLCAPS
+471,73,NAT,ALLCAPS
+472,73,PNAT,ALLCAPS
+473,74,PNAT,ALLCAPS
+474,74,PC,ALLCAPS
+475,74,DNS,ALLCAPS
+476,74,NAT,ALLCAPS
+477,84,Dan,PER
+478,84,PNAT,ALLCAPS
+479,85,XP,ALLCAPS
+480,85,PNAT,ALLCAPS
+481,85,OS,ALLCAPS
+482,86,Oss Hui,PER
+483,87,Brian,PER
+484,87,GPP,ALLCAPS
+485,87,EPS,ALLCAPS
+486,87,UE,ALLCAPS
+487,87,DNS,ALLCAPS
+488,87,NAT,ALLCAPS
+489,87,BOGON,ALLCAPS
+490,87,RFC,ALLCAPS
+491,87,NET,ALLCAPS
+492,87,IMS,ALLCAPS
+493,87,WKP,ALLCAPS
+494,87,HTP,ALLCAPS
+495,89,Cameron,PER
+496,89,Sri ill,PER
+497,89,NATDNS,ALLCAPS
+498,89,GPP,ALLCAPS
+499,90,GPP SA,ORG
+500,90,IETFGPP,ORG
+501,90,the SA,ORG
+502,90,Tao Sun China Mobile,ORG
+503,90,Shenzhen,LOC
+504,92,APN,ALLCAPS
+505,92,GPP,ALLCAPS
+506,92,NAT,ALLCAPS
+507,93,APN,ALLCAPS
+508,93,GPP,ALLCAPS
+509,93,NAT,ALLCAPS
+510,94,List,PER
+511,94,Hui Deng,PER
+512,94,Marc Blanchet,PER
+513,94,Outlook,ORG
+514,94,the,ORG
+515,94,EPS,ALLCAPS
+516,94,DNS,ALLCAPS
+517,94,DNSNAT,ALLCAPS
+518,95,UE,ALLCAPS
+519,95,GPP,ALLCAPS
+520,95,IS,ALLCAPS
+521,95,EPS,ALLCAPS
+522,95,PDP,ALLCAPS
+523,95,DNS,ALLCAPS
+524,95,APN,ALLCAPS
+525,95,NAT,ALLCAPS
+526,95,IMS,ORG
+527,96,Sri,PER
+528,97,NAT,ORG
+529,97,APN,ALLCAPS
+530,98,Brian,PER
+531,98,Rel,PER
+532,98,EPS,ORG
+533,98,PDN,ALLCAPS
+534,99,Hi Raj I,PER
+535,99,Rel PDN,ORG
+536,99,PDN,ALLCAPS
+537,99,UE,ALLCAPS
+538,99,DNS,ALLCAPS
+539,100,Brian,PER
+540,100,GPP,ORG
+541,100,UE,ALLCAPS
+542,100,PDP,ALLCAPS
+543,100,AFAICT,ALLCAPS
+544,100,DS,ALLCAPS
+545,100,PDN,ALLCAPS
+546,100,EPS,ALLCAPS
+547,101,Hi Raj,PER
+548,101,DNS,ALLCAPS
+549,101,NAT,ALLCAPS
+550,102,Cameron Byrne,PER
+551,102,TMobile,PER
+552,102,USA,LOC
+553,102,NAT,ALLCAPS
+554,102,DNS,ALLCAPS
+555,102,AA,ALLCAPS
+556,102,NATDNS,ALLCAPS
+557,102,OR,ALLCAPS
+558,103,Brian,PER
+559,103,WG Basicall,PER
+560,103,DS,ALLCAPS
+561,103,PDN,ALLCAPS
+562,103,DNS,ALLCAPS
+563,103,AAAA,ALLCAPS
+564,104,Brian,PER
+565,105,Sri,PER
+566,105,wwwapplicationcom,PER
+567,105,Brian,PER
+568,105,IP,ALLCAPS
+569,105,OS,ALLCAPS
+570,105,NAT,ALLCAPS
+571,106,Raj,PER
+572,106,stack,PER
+573,106,Brian BasavarajPatilnokiacom BasavarajPatilnokiacom,PER
+574,106,GPP,ORG
+575,106,DNS,ALLCAPS
+576,106,NAT,ALLCAPS
+577,106,PDN,ALLCAPS
+578,106,REL,ALLCAPS
+579,106,DSN,ALLCAPS
+580,107,lebbatdotcogecoca,ORG
+581,107,RFC,ORG
+582,108,Internet Protocol,MISC
+583,108,RFC,ALLCAPS
+584,109,Raj,PER
+585,109,DS,ALLCAPS
+586,109,AF,ALLCAPS
+587,109,GPP,ALLCAPS
+588,109,PDN,ALLCAPS
+589,109,DNS,ALLCAPS
+590,109,GOING,ALLCAPS
+591,109,TO,ALLCAPS
+592,110,BasavarajPatilnokiacom,ORG
+593,110,escribi,PER
+594,111,IPvonly,ORG
+595,111,NAT,ORG
+596,111,DS,ORG
+597,111,Cameron Byrne,PER
+598,111,TMobile USA,PER
+599,112,DS,ALLCAPS
+600,112,GPP,ALLCAPS
+601,112,MM,ALLCAPS
+602,112,applicationsservices,ORG
+603,113,GPP,ORG
+604,113,GGSN,ORG
+605,113,DS,ORG
+606,113,MM,ALLCAPS
+607,113,IP,ALLCAPS
+608,113,NAT,ALLCAPS
+609,114,BasavarajPatiln okiacom BasavarajPatilnokiacomA,PER
+610,114,haveietforg,PER
+611,114,PM,PER
+612,114,Cameron Byrne,PER
+613,114,PM lebbatdotcogecoca,PER
+614,114,youA,PER
+615,114,GPP,PER
+616,114,IPvonly,PER
+617,114,Wassim,PER
+618,114,cblistgmailcomA,ORG
+619,114,BSmithbellca,ORG
+620,114,AMA,ORG
+621,114,lebbatdotcogecoca,ORG
+622,114,PMA,ALLCAPS
+623,114,BEHAVE,ALLCAPS
+624,114,FW,ALLCAPS
+625,114,DNS,ALLCAPS
+626,114,NAT,ALLCAPS
+627,114,IP,ALLCAPS
+628,114,AAI,ALLCAPS
+629,114,AAA,ALLCAPS
+630,115,MM,PER
+631,115,United States,LOC
+632,115,North South West,LOC
+633,115,East region,LOC
+634,115,USA,LOC
+635,115,coast,LOC
+636,115,BOGON,ORG
+637,115,IANA,ORG
+638,115,USA Government,ORG
+639,115,Internet,ORG
+640,115,RFC,ALLCAPS
+641,115,IP,ALLCAPS
+642,115,SIP,ALLCAPS
+643,115,IMS,ALLCAPS
+644,115,SBC,ALLCAPS
+645,115,BBUA,ALLCAPS
+646,115,NAT,ALLCAPS
+647,115,LSN,ALLCAPS
+648,115,CGN,ALLCAPS
+649,115,DNS,ALLCAPS
+650,115,DS,ALLCAPS
+651,116,Cameron,PER
+652,116,Bo Zhou,PER
+653,116,EFEBBBEBABA,PER
+654,116,Cameron Byrne,PER
+655,116,behaveietforg,PER
+656,116,TMobile USA,PER
+657,116,mailtogvbouncesietforg EBBAEAA,ORG
+658,116,EBBECEA EBEBBBEBABA,ORG
+659,116,BSmithbellca,ORG
+660,116,EBBBEA,ORG
+661,116,IPvonly,ORG
+662,116,DS,ORG
+663,116,EAE,ALLCAPS
+664,116,BEHAVE,ALLCAPS
+665,116,FW,ALLCAPS
+666,116,DNS,ALLCAPS
+667,116,NAT,ALLCAPS
+668,116,LTE,ALLCAPS
+669,117,Cameron,PER
+670,117,Hong,PER
+671,117,Cameron Byrne,PER
+672,117,BSmithbellca,PER
+673,117,Bo Zhou,PER
+674,117,gvbouncesietforg mailtogvbouncesietforg,PER
+675,117,Liu,ORG
+676,117,IPvonly,ORG
+677,117,NAT,ALLCAPS
+678,117,VIP,ALLCAPS
+679,117,BABCFECCB,ALLCAPS
+680,117,BFABED,ALLCAPS
+681,117,DDCBA,ALLCAPS
+682,117,BACBCDCABBCE,ALLCAPS
+683,117,CEADCCD,ALLCAPS
+684,117,CADBCFECCB,ALLCAPS
+685,117,BADCBCD,ALLCAPS
+686,117,DFCCE,ALLCAPS
+687,117,BFBB,ALLCAPS
+688,117,BEHAVE,ALLCAPS
+689,117,FW,ALLCAPS
+690,117,DNS,ALLCAPS
+691,117,DS,ALLCAPS
+692,117,USA,ALLCAPS
+693,117,LTE,ALLCAPS
+694,118,Ie,PER
+695,118,IPvonly,PER
+696,118,DShosts,PER
+697,118,DShost,ORG
+698,118,DNS,ALLCAPS
+699,118,AAAA,ALLCAPS
+700,118,NAT,ALLCAPS
+701,118,RFC,ALLCAPS
+702,118,AFAIK,ALLCAPS
+703,119,Brian,PER
+704,119,Jouni,PER
+705,119,BasavarajPatilnokiacom,PER
+706,119,PDN,ALLCAPS
+707,119,DNS,ALLCAPS
+708,119,NAT,ALLCAPS
+709,119,UE,ORG
+710,121,BasavarajPatilnokiacom,PER
+711,121,escribi,PER
+712,122,DShost,ORG
+713,122,NAT,ALLCAPS
+714,122,DNS,ALLCAPS
+715,122,DS,ALLCAPS
+716,122,OR,ALLCAPS
+717,122,GPP,ALLCAPS
+718,122,HSS,ALLCAPS
+719,122,APN,ALLCAPS
+720,122,GGSN,ALLCAPS
+721,122,PGW,ALLCAPS
+722,122,EITHER,ALLCAPS
+723,122,AAAA,ALLCAPS
+724,122,RFC,ALLCAPS
+725,123,DS,ALLCAPS
+726,123,DNS,ALLCAPS
+727,124,DS,ORG
+728,124,OS,ORG
+729,124,DNS,ALLCAPS
+730,124,AAAA,ALLCAPS
+731,125,GPP,ORG
+732,125,PCO,ORG
+733,125,DNS,ALLCAPS
+734,125,PDP,ALLCAPS
+735,125,OS,ALLCAPS
+736,125,AAAA,ALLCAPS
+737,125,DN,ALLCAPS
+738,125,AFAIK,ALLCAPS
+739,126,operator,PER
+740,126,WiFi,PER
+741,126,my android,PER
+742,126,DShost,ORG
+743,126,DNS,ALLCAPS
+744,126,DS,ALLCAPS
+745,126,GPP,ALLCAPS
+746,126,PDP,ALLCAPS
+747,126,EPS,ALLCAPS
+748,126,APN,ALLCAPS
+749,126,HSS,ALLCAPS
+750,126,AAAA,ALLCAPS
+751,126,NAT,ALLCAPS
+752,126,RFC,ALLCAPS
+753,127,Cameron,PER
+754,127,Ipv,PER
+755,127,EE,ALLCAPS
+756,127,NAT,ALLCAPS
+757,127,IP,ALLCAPS
+758,127,VS,ALLCAPS
+759,127,DS,ALLCAPS
+760,127,DNS,ALLCAPS
+761,127,UE,ALLCAPS
+762,127,PDN,ALLCAPS
+763,127,SIP,ALLCAPS
+764,127,SBC,ALLCAPS
+765,127,SGWPGW,ALLCAPS
+766,127,SBCs,ORG
+767,127,BBUAs,ORG
+768,127,Internet,ORG
+769,127,BBUA,ORG
+770,128,KUDOS,PER
+771,128,Nokia,ORG
+772,128,Google,ORG
+773,128,BEHAVE,ORG
+774,128,Verizon,ORG
+775,128,TMobile,ORG
+776,128,USA,ALLCAPS
+777,128,NAT,ALLCAPS
+778,128,NATPT,ALLCAPS
+779,128,DNS,ALLCAPS
+780,128,SMS,ALLCAPS
+781,128,LTE,ALLCAPS
+782,128,IMS,ALLCAPS
+783,128,CGN,ALLCAPS
+784,128,LSN,ALLCAPS
+785,128,DS,ALLCAPS
+786,128,EE,ALLCAPS
+787,129,AAAA,ALLCAPS
+788,129,OS,ALLCAPS
+789,129,DNS,ALLCAPS
+790,131,Cameron and I,PER
+791,131,People,PER
+792,131,DNS,ALLCAPS
+793,131,NAT,ALLCAPS
+794,131,IP,ALLCAPS
+795,131,FTP,ALLCAPS
+796,132,Brian I,PER
+797,132,Dapeng Liu,PER
+798,132,HI,ALLCAPS
+799,132,DNS,ALLCAPS
+800,132,IP,ALLCAPS
+801,133,DS,ORG
+802,133,AM,ORG
+803,133,David Crowe,PER
+804,133,DNS,ALLCAPS
+805,134,Gv,PER
+806,134,IPvonly,PER
+807,134,BEHAVE,ALLCAPS
+808,134,DNS,ALLCAPS
+809,134,AAAA,ALLCAPS
+810,134,DHCP,ALLCAPS
+811,135,mobility,PER
+812,135,Dan Wing dwingciscocomA,PER
+813,135,gvietforg,PER
+814,135,behaveietforgA,PER
+815,135,DHCP,ORG
+816,135,AAAA,ALLCAPS
+817,135,WG,ALLCAPS
+818,135,PMA,ALLCAPS
+819,135,DNS,ALLCAPS
+820,135,BEHAVEA,ALLCAPS
+821,136,guy,PER
+822,136,Windows,MISC
+823,136,FTP,ALLCAPS
+824,136,NAT,ALLCAPS
+825,136,IP,ALLCAPS
+826,136,GPP,ALLCAPS
+827,137,DNS,ALLCAPS
+828,137,AAAA,ALLCAPS
+829,137,FQDN,ALLCAPS
+830,137,RFC,ALLCAPS
+831,138,Dan,PER
+832,138,drafthaddad,PER
+833,138,Couple of us,PER
+834,138,Teemu,PER
+835,138,GPP,PER
+836,138,Wassims,PER
+837,138,MIPv,ORG
+838,139,BasavarajPatilnokiacom,ORG
+839,139,DNS,ALLCAPS
+840,139,Internet,MISC
+841,140,Brian,PER
+842,140,Windows,MISC
+843,140,RFC,ALLCAPS
+844,140,AFAIK,ALLCAPS
+845,141,IP,ALLCAPS
+846,142,NAT,ALLCAPS
+847,142,HDS,ALLCAPS
+848,142,DNS,ALLCAPS
+849,142,AAAA,ALLCAPS
+850,142,NSP,ALLCAPS
+851,142,BFABED,ALLCAPS
+852,144,Dan,PER
+853,144,draftboucadairbehavednsa,PER
+854,144,Zhen,PER
+855,144,RR,ALLCAPS
+856,145,IAKaGkgRGFuDQoNCkkgdGhpbmsgdGhlIHNvbHVaWuIDIgdlsbCBpbmNyZWFzZSBaGUgYt,ORG
+857,145,IHdpdGggREhDUFYIHNlcnZlciwgdGhlbiBaGVzZSBdgREhDUCBwcmjZWRcmVzIGNhbiBz,DIG
+858,146,Behcet Sarikaya escribi I,PER
+859,146,MIPv,PER
+860,146,WK,ALLCAPS
+861,146,NAT,ALLCAPS
+862,146,DNS,ALLCAPS
+863,147,S,PER
+864,147,BEHAVE,PER
+865,148,DHCPv,ORG
+866,148,mailtogvbouncesietforg,PER
+867,148,Dan Wing,PER
+868,148,MUST,ALLCAPS
+869,148,RFC,ALLCAPS
+870,149,BEHAVE,PER
+871,149,DNS,ALLCAPS
+872,149,NATDNS,ALLCAPS
+873,150,MN,ORG
+874,150,NAT,ALLCAPS
+875,150,DNS,ALLCAPS
+876,150,AAAA,ALLCAPS
+877,150,NSP,ALLCAPS
+878,150,RFC,ALLCAPS
+879,151,BasavarajPatilnokiacom,ORG
+880,151,Firefoxs,ORG
+881,151,OS,ORG
+882,151,OSs,ORG
+883,151,IPvonly,ORG
+884,151,DNS,ALLCAPS
+885,151,AAAA,ALLCAPS
+886,152,marcelo bagnulo braun,PER
+887,152,rceloitucmesA,PER
+888,152,Sarikaya sarikayaieeeorgA,PER
+889,152,dwingciscocom,PER
+890,152,Sarikaya escribiFA,PER
+891,152,AAAA,ALLCAPS
+892,152,WG,ALLCAPS
+893,152,AMA,ALLCAPS
+894,152,BEHAVE,ALLCAPS
+895,152,DNS,ALLCAPS
+896,152,NAT,ALLCAPS
+897,152,WK,ALLCAPS
+898,152,AA,ALLCAPS
+899,153,Dan Wing,PER
+900,154,Behcet Sarikaya escribi,PER
+901,154,the,PER
+902,154,WKP,ALLCAPS
+903,155,Internet,ORG
+904,155,NAT,ALLCAPS
+905,155,DNS,ALLCAPS
+906,155,AAAA,ALLCAPS
+907,155,FFB,ALLCAPS
+908,155,TCP,ALLCAPS
+909,155,SYN,ALLCAPS
+910,157,marcelo bagnulo braun,PER
+911,157,rceloitucmesA,PER
+912,157,Behcet Sarikaya sarikayaieeeorgA,PER
+913,157,dwingciscocom,PER
+914,157,behaveietforgA,PER
+915,157,draftwingbehavednsconfigA,PER
+916,157,Sarikaya escribiFA,PER
+917,157,gvietforg,PER
+918,157,A,PER
+919,157,AAAA,ALLCAPS
+920,157,WG,ALLCAPS
+921,157,PMA,ALLCAPS
+922,157,BEHAVE,ALLCAPS
+923,157,DNS,ALLCAPS
+924,157,AMA,ALLCAPS
+925,157,NAT,ALLCAPS
+926,157,WK,ALLCAPS
+927,157,WKP,ALLCAPS
+928,157,NA,ALLCAPS
+929,157,LMA,ALLCAPS
+930,157,HA,ALLCAPS
+931,158,Sarikaya,ORG
+932,158,MIP,ORG
+933,158,escribi,PER
+934,158,HA,LOC
+935,158,DNS,ALLCAPS
+936,158,NAT,ALLCAPS
+937,158,BT,ALLCAPS
+938,158,WKP,ALLCAPS
+939,158,PMIP,ALLCAPS
+940,159,Dan Wing,PER
+941,159,WKP,ALLCAPS
+942,159,RR,ALLCAPS
+943,159,AAAA,ALLCAPS
+944,159,MN,ALLCAPS
+945,159,CN,ALLCAPS
+946,159,NAT,ALLCAPS
+947,160,Dan Broader,PER
+948,160,David Crowe,PER
+949,160,Dan Wing,PER
+950,160,IPvonly,ORG
+951,160,AM,ORG
+952,160,DS,ALLCAPS
+953,160,NAT,ALLCAPS
+954,160,AAAA,ALLCAPS
+955,161,Dan,PER
+956,161,sietforghtmldraftboucadairbehavednsdiscovery,PER
+957,161,client,PER
+958,161,la part de Dan,PER
+959,161,Zhen Cao,PER
+960,161,DS,ORG
+961,161,DNS,ALLCAPS
+962,161,SRV,ALLCAPS
+963,161,WG,ALLCAPS
+964,161,BEHAVE,ALLCAPS
+965,161,NATDNS,ALLCAPS
+966,163,draftwingbehavednsconfig,ORG
+967,163,RFC,ORG
+968,163,NAT,ALLCAPS
+969,163,DNS,ALLCAPS
+970,163,AAAA,ALLCAPS
+971,163,DHCP,ALLCAPS
+972,164,BasavarajPatilnokiacom,PER
+973,164,Skype,PER
+974,164,IPvonly,ORG
+975,164,IETF,ORG
+976,164,OS,ALLCAPS
+977,164,NAT,ALLCAPS
+978,164,TCP,ALLCAPS
+979,164,UDP,ALLCAPS
+980,164,RSVP,ALLCAPS
+981,164,SCTP,ALLCAPS
+982,164,DCCP,ALLCAPS
+983,164,AAAA,ALLCAPS
+984,164,DNS,ALLCAPS
+985,165,Dan,PER
+986,165,IVI,ORG
+987,165,SIPNAT,ORG
+988,165,HTTP,ALLCAPS
+989,165,PS,ALLCAPS
+990,165,OK,ALLCAPS
+991,166,IVISIPNATHTTP,ORG
+992,166,IPvonly,ORG
+993,167,marcelo bagnulo braun,PER
+994,167,rceloitucmesA,PER
+995,167,Dan,PER
+996,167,dwingciscocom,PER
+997,167,behaveietforgA,PER
+998,167,Sarikaya escribiFA,PER
+999,167,gvietforg,PER
+1000,167,mobilit y,PER
+1001,167,Behcet,ORG
+1002,167,marcelo,ORG
+1003,167,AAAA,ALLCAPS
+1004,167,WG,ALLCAPS
+1005,167,AMA,ALLCAPS
+1006,167,BEHAVE,ALLCAPS
+1007,167,DNS,ALLCAPS
+1008,167,PMA,ALLCAPS
+1009,167,NAT,ALLCAPS
+1010,167,WK,ALLCAPS
+1011,167,WKP,ALLCAPS
+1012,167,LMA,ALLCAPS
+1013,167,HA,ALLCAPS
+1014,167,DSL,ALLCAPS
+1015,167,MIPA,ALLCAPS
+1016,167,BT,ALLCAPS
+1017,167,PMIP,ALLCAPS
+1018,167,DNSA,ALLCAPS
+1019,168,RFC,ORG
+1020,168,BEHAVE,ORG
+1021,168,NATPT,ALLCAPS
+1022,168,DNS,ALLCAPS
+1023,169,Andrew Sullivan escribi,PER
+1024,170,Dan,PER
+1025,170,NATPT,ALLCAPS
+1026,171,Hotel Nikko,LOC
+1027,171,the Hilton San Francisco,LOC
+1028,172,IPvonly,ORG
+1029,172,NAT,ALLCAPS
+1030,172,DNS,ALLCAPS
+1031,172,NATPT,ALLCAPS
+1032,172,XP,ALLCAPS
+1033,172,HQ,ALLCAPS
+1034,173,Nobody,PER
+1035,173,David Crowe,PER
+1036,173,Brian E Carpenter,PER
+1037,173,AM,ORG
+1038,174,David,PER
+1039,174,Brian Carpenter,PER
+1040,175,GPP,ALLCAPS
+1041,175,TR,ALLCAPS
+1042,176,Julien I,PER
+1043,176,GPP,ALLCAPS
+1044,176,TR,ALLCAPS
+1045,178,JulienAA,PER
+1046,178,Julien Bournelle julien bournellegmailcomA,PER
+1047,178,gvietforgA,PER
+1048,178,AAAA,ALLCAPS
+1049,178,AMA,ALLCAPS
+1050,178,WS,ALLCAPS
+1051,178,GPPIETF,ALLCAPS
+1052,178,PP,ALLCAPS
+1053,178,TR,ALLCAPS
+1054,178,GPP,ALLCAPS
+1055,179,Behcet Sarikaya,PER
+1056,179,Behcet,PER
+1057,180,Hi Raj,PER
+1058,180,ba sis,DIG
+1059,180,withIETFDocs,DIG
+1060,180,GPP,ALLCAPS
+1061,180,TR,ALLCAPS
+1062,181,IPWzip,ORG
+1063,181,Laganier Julien,PER
+1064,181,TR,ALLCAPS
+1065,182,Behcet Sarikaya,PER
+1066,182,behcetsarikayayahoocomA,PER
+1067,182,Julien Bournelle,PER
+1068,182,Juli en Bournelle,PER
+1069,182,Sarikaya,ORG
+1070,182,gvietforgA,ORG
+1071,182,listA,DIG
+1072,182,AMA,ALLCAPS
+1073,182,WS,ALLCAPS
+1074,182,GPPIETF,ALLCAPS
+1075,182,GPP,ALLCAPS
+1076,182,TR,ALLCAPS
+1077,183,SA,ORG
+1078,183,Julien,PER
+1079,183,TR,ALLCAPS
+1080,184,FYI,ALLCAPS
+1081,184,TR,ALLCAPS
+1082,184,PCR,ALLCAPS
+1083,185,Julien,PER
+1084,185,IETF,ORG
+1085,185,crossSDO,ORG
+1086,185,Hiroshima,LOC
+1087,186,Jari,PER
+1088,186,MacOS,MISC
+1089,186,OS,ALLCAPS
+1090,186,BSD,ALLCAPS
+1091,186,ALL,ALLCAPS
+1092,186,VERY,ALLCAPS
+1093,186,IP,ALLCAPS
+1094,186,APN,ALLCAPS
+1095,187,Jari Arkko,PER
+1096,187,EST,ALLCAPS
+1097,188,Jari Inline,PER
+1098,188,my personal,PER
+1099,188,Oss,ORG
+1100,188,LIPA,ORG
+1101,188,APN,ALLCAPS
+1102,190,Zhenqiang,PER
+1103,190,lizhenqiang chinamobilecomATo Laganier Julien julienlqualcommcom davidb,PER
+1104,190,sarikayaieeeorg sarikayaie,PER
+1105,190,EDEECAFEBCBA,ORG
+1106,190,davidb inetorangeftgroupcom davidbinetorangeftgroupcom,ORG
+1107,190,sarikayaie,ORG
+1108,190,GPP SA,ORG
+1109,190,toCA,ORG
+1110,190,GPPAA,ORG
+1111,190,UE,ORG
+1112,190,requirementAAI,ORG
+1113,190,Shenzhen ChinaCA,LOC
+1114,190,PP,ALLCAPS
+1115,190,PD,ALLCAPS
+1116,191,GPP,ALLCAPS
+1117,191,DOCTYPE,ALLCAPS
+1118,191,PUBLIC,ALLCAPS
+1119,191,WCDTD,ALLCAPS
+1120,191,HTML,ALLCAPS
+1121,191,IP,ALLCAPS
+1122,191,RFC,ALLCAPS
+1123,191,UE,ALLCAPS
+1124,191,PDP,ALLCAPS
+1125,191,GGSN,ALLCAPS
+1126,191,MS,ALLCAPS
+1127,191,MM,ALLCAPS
+1128,191,APN,ALLCAPS
+1129,191,NAT,ALLCAPS
+1130,191,DS,ALLCAPS
+1131,192,Jari,PER
+1132,192,NAT,ALLCAPS
+1133,192,GPP,ALLCAPS
+1134,192,GGSN,ALLCAPS
+1135,192,RFC,ALLCAPS
+1136,193,ID,ALLCAPS
+1137,193,GPP,ALLCAPS
+1138,196,Fred Balazs,PER
+1139,196,Gv We,PER
+1140,196,gppIETF,ORG
+1141,196,San Francisco,LOC
+1142,198,IPWzip,ORG
+1143,198,FTP,ALLCAPS
+1144,199,Gateway,ORG
+1145,200,Feedback,PER
+1146,200,Jari,PER
+1147,200,IETF,ORG
+1148,201,hosts,PER
+1149,201,Lite,PER
+1150,201,RDto,ORG
+1151,201,NAT,ALLCAPS
+1152,201,GPP,ALLCAPS
+1153,201,PPP,ALLCAPS
+1154,201,UE,ALLCAPS
+1155,201,IID,ALLCAPS
+1156,201,PD,ALLCAPS
+1157,201,GW,ALLCAPS
+1158,201,PDP,ALLCAPS
+1159,201,EPS,ALLCAPS
+1160,201,RFP,ALLCAPS
+1161,201,IETF,ALLCAPS
+1162,202,Gert,ORG
+1163,202,SpaceNet AG Vorstand Sebastian,ORG
+1164,202,Bomhard JosephDollingerBogen Aufsichtsratsvors A GrundnerCulemann D Muenchen HRB AG Muenchen Tel UStIdNr,ORG
+1165,203,Cameron,PER
+1166,205,Mikael Abrahamsson,PER
+1167,205,Cameron,PER
+1168,205,ISP,ORG
+1169,205,the GPP,ORG
+1170,205,GGSN,ALLCAPS
+1171,205,AM,ALLCAPS
+1172,205,PGW,ALLCAPS
+1173,205,PDP,ALLCAPS
+1174,205,REQUIRE,ALLCAPS
+1175,206,providerISP,ORG
+1176,207,Mikael Abrahamsson,PER
+1177,207,GGSN,ALLCAPS
+1178,207,AM,ALLCAPS
+1179,208,Stateless,ORG
+1180,208,others,PER
+1181,208,Simon,PER
+1182,208,RFC,ALLCAPS
+1183,208,STUNTURN,ALLCAPS
+1184,209,Ethernet,ORG
+1185,209,WLAN,ORG
+1186,209,RFC,ALLCAPS
+1187,209,SLAAC,ALLCAPS
+1188,209,MUST,ALLCAPS
+1189,209,MAY,ALLCAPS
+1190,209,IID,ALLCAPS
+1191,209,IP,ALLCAPS
+1192,209,ND,ALLCAPS
+1193,210,Feb Cameron Byrne cblistgmailcom,PER
+1194,210,RE,ALLCAPS
+1195,210,GGSN,ALLCAPS
+1196,211,Simon Perreault,PER
+1197,211,RFC,ALLCAPS
+1198,212,Cheers Suresh,PER
+1199,213,RFC,ORG
+1200,213,Simon,ORG
+1201,213,GPP,ALLCAPS
+1202,213,STUNTURN,ALLCAPS
+1203,214,LTE,ALLCAPS
+1204,214,CLOSE,ALLCAPS
+1205,215,France Telecom Group,ORG
+1206,215,ND,ALLCAPS
+1207,216,Mikael Abrahamsson,PER
+1208,216,each,PER
+1209,216,EPC,ORG
+1210,216,GGG,ORG
+1211,216,GPP,ALLCAPS
+1212,216,AM,ALLCAPS
+1213,216,LTE,ALLCAPS
+1214,216,PGW,ALLCAPS
+1215,216,UMTS,ALLCAPS
+1216,216,SLAAC,ALLCAPS
+1217,216,ISP,ALLCAPS
+1218,216,MUST,ALLCAPS
+1219,216,SHOULD,ALLCAPS
+1220,217,Nokias,ORG
+1221,217,Shanghai WS,ORG
+1222,217,SGSNs,ORG
+1223,217,GPP,ALLCAPS
+1224,217,PDPPDN,ALLCAPS
+1225,217,TR,ALLCAPS
+1226,217,PDP,ALLCAPS
+1227,218,MME,ALLCAPS
+1228,218,SPGW,ALLCAPS
+1229,218,LTE,ALLCAPS
+1230,219,Fredrik,PER
+1231,219,folks,PER
+1232,219,S,ORG
+1233,219,Nokia,ORG
+1234,219,SGSNs,ORG
+1235,219,Windows OS,MISC
+1236,219,PDP,ALLCAPS
+1237,220,Mikael Abrahamsson,PER
+1238,220,MME,ALLCAPS
+1239,220,PM,ALLCAPS
+1240,220,CPU,ALLCAPS
+1241,220,MM,ALLCAPS
+1242,220,LTE,ALLCAPS
+1243,220,ATCA,ORG
+1244,220,Moores,ORG
+1245,220,SPGW,ORG
+1246,220,EPC,ORG
+1247,220,New York,LOC
+1248,221,Fredrik Rajeev I,PER
+1249,221,IP,ALLCAPS
+1250,221,HTTP,ALLCAPS
+1251,221,MIDP,ALLCAPS
+1252,221,IDP,ALLCAPS
+1253,221,PDN,ALLCAPS
+1254,221,LTE,ALLCAPS
+1255,221,DNS,ALLCAPS
+1256,222,Internet,MISC
+1257,222,IANA,ORG
+1258,222,LSN,ORG
+1259,222,HTTP,ALLCAPS
+1260,222,IP,ALLCAPS
+1261,222,MIDP,ALLCAPS
+1262,222,DNS,ALLCAPS
+1263,222,PDP,ALLCAPS
+1264,222,NAT,ALLCAPS
+1265,222,CGN,ALLCAPS
+1266,222,OS,ALLCAPS
+1267,222,VP,ALLCAPS
+1268,222,CAN,ALLCAPS
+1269,222,NOT,ALLCAPS
+1270,222,IMS,ALLCAPS
+1271,222,EE,ALLCAPS
+1272,222,AS,ALLCAPS
+1273,222,SOON,ALLCAPS
+1274,222,POSSIBLE,ALLCAPS
+1275,223,Jari,PER
+1276,223,Lars,PER
+1277,223,IETF,ORG
+1278,223,UE,ORG
+1279,224,Cameron I,PER
+1280,224,MM,ALLCAPS
+1281,225,Rajeev,PER
+1282,225,David Crowe,PER
+1283,226,Teemu We,PER
+1284,226,Google,PER
+1285,226,you You,PER
+1286,226,Fredrik,PER
+1287,226,me Nobody,PER
+1288,226,Android Google,PER
+1289,226,IETF,PER
+1290,226,GPP,ORG
+1291,226,Dualstack,ORG
+1292,226,IANA,ORG
+1293,226,IPvonly,ORG
+1294,226,CGN,ALLCAPS
+1295,226,MM,ALLCAPS
+1296,226,VERY,ALLCAPS
+1297,226,UE,ALLCAPS
+1298,226,GA,ALLCAPS
+1299,226,NAT,ALLCAPS
+1300,226,RAN,ALLCAPS
+1301,226,GGSN,ALLCAPS
+1302,226,APN,ALLCAPS
+1303,226,HSS,ALLCAPS
+1304,226,San Francisco,LOC
+1305,227,Teemu,PER
+1306,227,operators,ORG
+1307,227,PDN,ALLCAPS
+1308,227,APN,ALLCAPS
+1309,227,LTE,ALLCAPS
+1310,227,IP,ALLCAPS
+1311,227,UE,ALLCAPS
+1312,228,David,PER
+1313,229,Apple,ORG
+1314,229,Microsoft,ORG
+1315,229,Skype,ORG
+1316,229,IETFs ICE,ORG
+1317,229,Internet,ORG
+1318,229,my Mac,PER
+1319,229,users,PER
+1320,229,IP,ALLCAPS
+1321,229,NAT,ALLCAPS
+1322,229,RFC,ALLCAPS
+1323,230,Dan,PER
+1324,230,skype,PER
+1325,230,Rajeev,PER
+1326,230,NAT,ALLCAPS
+1327,230,WLAN,ALLCAPS
+1328,230,MN,ALLCAPS
+1329,231,guy,PER
+1330,231,IETF,ORG
+1331,231,NAT,ALLCAPS
+1332,232,SBC BBUA,ORG
+1333,232,CGN,ORG
+1334,232,SBC,ORG
+1335,232,NAT,ALLCAPS
+1336,232,MPLS,ALLCAPS
+1337,232,VPN,ALLCAPS
+1338,232,MN,ALLCAPS
+1339,232,RFC,ALLCAPS
+1340,232,IMS,ALLCAPS
+1341,232,ATT,ALLCAPS
+1342,233,Especi,PER
+1343,233,Teemu,PER
+1344,233,Finland,LOC
+1345,233,MNMN,ALLCAPS
+1346,233,TV,ALLCAPS
+1347,233,AM,ALLCAPS
+1348,233,PDN,ALLCAPS
+1349,233,WLAN,ALLCAPS
+1350,233,NAT,ALLCAPS
+1351,233,RFC,ALLCAPS
+1352,234,Cameron,PER
+1353,234,NAT,ALLCAPS
+1354,234,HT,ALLCAPS
+1355,235,Pvonly,PER
+1356,235,my VP,PER
+1357,235,android,PER
+1358,235,iPhone,PER
+1359,235,NATPT,ALLCAPS
+1360,235,DNSALG,ALLCAPS
+1361,235,DNS,ALLCAPS
+1362,235,SDK,ALLCAPS
+1363,236,DSMIP,ORG
+1364,236,Ipv,ORG
+1365,236,GPP,ALLCAPS
+1366,236,EPS,ALLCAPS
+1367,236,BOSS,ALLCAPS
+1368,237,Simon,PER
+1369,237,STUNTURN,DIG
+1370,238,PNAT,DIG
+1371,238,SF,LOC
+1372,239,Googles,ORG
+1373,239,DNS,ALLCAPS
+1374,239,XMPP,ALLCAPS
+1375,239,SIP,ALLCAPS
+1376,239,SMTPXMPPSIP,ALLCAPS
+1377,239,NAT,ALLCAPS
+1378,239,BEHAVE,ALLCAPS
+1379,240,Teemu,PER
+1380,240,Dan I,PER
+1381,240,Camerons,PER
+1382,240,IPvonly,ORG
+1383,240,PDN,ALLCAPS
+1384,240,MN,ALLCAPS
+1385,240,BTW,ALLCAPS
+1386,240,NAT,ALLCAPS
+1387,240,NET,ALLCAPS
+1388,240,AM,ALLCAPS
+1389,240,GOING,ALLCAPS
+1390,240,TO,ALLCAPS
+1391,240,IP,ALLCAPS
+1392,240,MPLS,ALLCAPS
+1393,241,App,ORG
+1394,242,Dan,PER
+1395,242,DNSsec,ORG
+1396,242,DNS,ALLCAPS
+1397,242,NAT,ALLCAPS
+1398,242,PNAT,ALLCAPS
+1399,242,ALG,ALLCAPS
+1400,243,Jari I,PER
+1401,243,Cao Zhen,PER
+1402,243,OS,ALLCAPS
+1403,244,Cameron,PER
+1404,244,Cao Zhen China,PER
+1405,244,DS,ORG
+1406,244,NAT,ALLCAPS
+1407,245,Rajeev,PER
+1408,245,NAT,ALLCAPS
+1409,245,GGSN,ALLCAPS
+1410,245,MASS,ALLCAPS
+1411,245,MMIMS,ALLCAPS
+1412,246,MNMN,ORG
+1413,246,AAAA,ALLCAPS
+1414,247,PDN,ALLCAPS
+1415,247,UE,ALLCAPS
+1416,247,TCP,ALLCAPS
+1417,247,NET,ALLCAPS
+1418,247,ET,ALLCAPS
+1419,247,TCPIP,ALLCAPS
+1420,247,XMPP,ALLCAPS
+1421,247,IP,ALLCAPS
+1422,247,WLAN,ALLCAPS
+1423,247,NAT,ALLCAPS
+1424,247,GW,ALLCAPS
+1425,247,UEs,ORG
+1426,248,Ebay,ORG
+1427,248,CGN,ORG
+1428,248,UEs,ORG
+1429,248,PDN,ALLCAPS
+1430,248,UE,ALLCAPS
+1431,248,NAT,ALLCAPS
+1432,248,TCP,ALLCAPS
+1433,248,NET,ALLCAPS
+1434,248,PDP,ALLCAPS
+1435,248,TCPIP,ALLCAPS
+1436,248,PXMPP,ALLCAPS
+1437,248,IP,ALLCAPS
+1438,248,WLAN,ALLCAPS
+1439,248,GW,ALLCAPS
+1440,248,NOT,ALLCAPS
+1441,248,OSS,ALLCAPS
+1442,249,Dear Hui,PER
+1443,249,Jouni,PER
+1444,249,DSMIP,ALLCAPS
+1445,249,IP,ALLCAPS
+1446,249,EPS,ALLCAPS
+1447,249,MN,ALLCAPS
+1448,250,Cameron,PER
+1449,250,GPP,ORG
+1450,250,PDP,ORG
+1451,250,AFAIK,ORG
+1452,250,GTP,ALLCAPS
+1453,251,Bittorrent,PER
+1454,251,user,PER
+1455,251,UE,ORG
+1456,251,DNS,ALLCAPS
+1457,251,SIP,ALLCAPS
+1458,251,FTP,ALLCAPS
+1459,251,RTCP,ALLCAPS
+1460,251,SMTP,ALLCAPS
+1461,251,HTTP,ALLCAPS
+1462,251,DSL,ALLCAPS
+1463,251,IP,ALLCAPS
+1464,251,RTSP,ALLCAPS
+1465,251,TTL,ALLCAPS
+1466,251,DNSSEC,ALLCAPS
+1467,252,PDN,ALLCAPS
+1468,252,MN,ALLCAPS
+1469,252,GPP,ALLCAPS
+1470,252,NET,ALLCAPS
+1471,252,LTE,ALLCAPS
+1472,252,NAT,ALLCAPS
+1473,252,IP,ALLCAPS
+1474,254,Hi Hui,PER
+1475,254,UE,ORG
+1476,254,NAT,ALLCAPS
+1477,254,PNAT,ALLCAPS
+1478,254,NET,ALLCAPS
+1479,254,BSD,ALLCAPS
+1480,255,Hello Hui,PER
+1481,255,Rajeev,PER
+1482,256,Sri Gundavelli sgundaveciscocom I,PER
+1483,256,NAT,ALLCAPS
+1484,256,PDN,ALLCAPS
+1485,256,GW,ALLCAPS
+1486,257,Dan You,PER
+1487,257,Dan Wing,PER
+1488,257,DNS,ALLCAPS
+1489,258,Jari,PER
+1490,258,IETF,ORG
+1491,258,GGSN,ORG
+1492,258,FYI,ALLCAPS
+1493,258,NAT,ALLCAPS
+1494,258,UE,ALLCAPS
+1495,258,NA,ALLCAPS
+1496,258,PS,ALLCAPS
+1497,259,GPPIETF,ORG
+1498,259,PNAT,ALLCAPS
+1499,259,NAT,ALLCAPS
+1500,259,ALG,ALLCAPS
+1501,259,DNS,ALLCAPS
+1502,259,SIP,ALLCAPS
+1503,259,XMPP,ALLCAPS
+1504,259,RTSP,ALLCAPS
+1505,259,NAPT,ALLCAPS
+1506,259,FTP,ALLCAPS
+1507,259,SMTP,ALLCAPS
+1508,259,IMAP,ALLCAPS
+1509,259,POP,ALLCAPS
+1510,259,HTTP,ALLCAPS
+1511,259,IE,ALLCAPS
+1512,259,AAAA,ALLCAPS
+1513,259,IETF,ALLCAPS
+1514,259,GROBJ,ALLCAPS
+1515,259,GRO,ALLCAPS
+1516,259,GPP,ALLCAPS
+1517,260,Fred,PER
+1518,261,Hi Hui,PER
+1519,261,UE,ALLCAPS
+1520,261,NAT,ALLCAPS
+1521,261,IPvonly,ORG
+1522,261,PDP,ORG
+1523,262,Hi Hui,PER
+1524,262,GPP,ALLCAPS
+1525,262,DSMIP,ALLCAPS
+1526,262,ID,ALLCAPS
+1527,262,RFC,ALLCAPS
+1528,262,AM,ALLCAPS
+1529,262,GOING,ALLCAPS
+1530,262,TO,ALLCAPS
+1531,262,IP,ALLCAPS
+1532,262,PGW,ALLCAPS
+1533,262,NAT,ALLCAPS
+1534,262,TR,ALLCAPS
+1535,262,UE,ORG
+1536,262,BEHAVE,ORG
+1537,263,Rajs,PER
+1538,263,UE,ORG
+1539,263,UEs,ORG
+1540,263,IP,ALLCAPS
+1541,263,DNS,ALLCAPS
+1542,264,Hi,PER
+1543,264,BTW,PER
+1544,264,draftkoodliipvinmobilenetworks,PER
+1545,264,NAT,ALLCAPS
+1546,264,IP,ALLCAPS
+1547,264,IMHO,ORG
+1548,265,Rajeev,PER
+1549,265,UE,ORG
+1550,265,devicesapplicationsnetworks,ORG
+1551,265,PGW,ALLCAPS
+1552,265,NAT,ALLCAPS
+1553,265,GPP,ALLCAPS
+1554,265,PP,ALLCAPS
+1555,265,GW,ALLCAPS
+1556,265,IP,ALLCAPS
+1557,266,Jouni,PER
+1558,266,Section,ORG
+1559,266,EPS,ALLCAPS
+1560,266,UE,ALLCAPS
+1561,266,IP,ALLCAPS
+1562,267,AS,ORG
+1563,267,IMHO,ORG
+1564,267,SGi,PER
+1565,267,NAT,ALLCAPS
+1566,267,PGW,ALLCAPS
+1567,267,IP,ALLCAPS
+1568,268,GPP,ORG
+1569,268,NAT,ALLCAPS
+1570,268,PGW,ALLCAPS
+1571,268,PDN,ALLCAPS
+1572,268,IP,ALLCAPS
+1573,269,UEs,ORG
+1574,269,NAT,ALLCAPS
+1575,270,GGSN,PER
+1576,270,folks,PER
+1577,270,IPvonly,PER
+1578,270,USA,LOC
+1579,270,San Francisco,LOC
+1580,270,GMXcom,ORG
+1581,270,TMobile,ORG
+1582,270,GPPIETF,ORG
+1583,270,TMobile USA,ORG
+1584,270,UE,ALLCAPS
+1585,270,RAN,ALLCAPS
+1586,270,PDP,ALLCAPS
+1587,270,RF,ALLCAPS
+1588,270,DNS,ALLCAPS
+1589,270,NAT,ALLCAPS
+1590,270,IMAP,ALLCAPS
+1591,270,APN,ALLCAPS
+1592,271,Cameron You,PER
+1593,271,Cameron Byrne,PER
+1594,271,cblistgmailcom,ORG
+1595,272,Gary Jones,PER
+1596,272,Cameorn,PER
+1597,272,the TMobile standards group,ORG
+1598,272,Android,ORG
+1599,272,SF,ALLCAPS
+1600,272,APN,ALLCAPS
+1601,273,Cameron Byrne cblistgmailcom,PER
+1602,274,Host,ORG
+1603,274,GPP SA,ORG
+1604,274,PNAT,ALLCAPS
+1605,274,ALG,ALLCAPS
+1606,275,jouni korhonen jouninospamgmailcom,PER
+1607,275,DSMIPv,PER
+1608,275,PM,ALLCAPS
+1609,275,EPS,ALLCAPS
+1610,275,TR,ALLCAPS
+1611,275,MN,ALLCAPS
+1612,276,BT,ORG
+1613,276,companies,ORG
+1614,276,SA,ORG
+1615,276,Nokia,ORG
+1616,276,NAT,ALLCAPS
+1617,276,NATPT,ALLCAPS
+1618,277,David Crowe,PER
+1619,277,UE,ALLCAPS
+1620,277,IP,ALLCAPS
+1621,277,NAT,ALLCAPS
+1622,278,yourself We,PER
+1623,278,CMCC,ORG
+1624,279,IPvonly,ORG
+1625,279,UE,ORG
+1626,279,NAT,ALLCAPS
+1627,279,PDP,ALLCAPS
+1628,280,GPP,ALLCAPS
+1629,280,ID,ALLCAPS
+1630,280,RFC,ORG
+1631,280,SA,ORG
+1632,281,BitTorrent,ORG
+1633,281,BitTorrents,ORG
+1634,281,BEHAVE,ALLCAPS
+1635,282,Cameron I,PER
+1636,282,David Crowe,PER
+1637,282,Cameron Byrne,PER
+1638,282,NAT,ORG
+1639,282,UE,ORG
+1640,282,AM,ORG
+1641,283,David Crowe,PER
+1642,284,Cameron,PER
+1643,285,you I,PER
+1644,285,turtle,PER
+1645,287,Will,PER
+1646,287,Ovi,PER
+1647,287,UE,PER
+1648,287,Gary Jones,PER
+1649,287,IPvonly UE,ORG
+1650,287,wwwwhatismyipvnet,ORG
+1651,287,San Francisco,LOC
+1652,288,Dan Cameron,PER
+1653,288,David At,PER
+1654,288,Dan Wing,PER
+1655,288,PM,ORG
+1656,289,Cameron,PER
+1657,289,Even I,PER
+1658,289,David,PER
+1659,289,Cameron Byrne,PER
+1660,289,PM,ALLCAPS
+1661,290,GGSN,ORG
+1662,290,AFAIK,ALLCAPS
+1663,290,IMS,ALLCAPS
+1664,290,NAT,ALLCAPS
+1665,291,Dan,PER
+1666,291,Camerons,PER
+1667,291,PNAT,ALLCAPS
+1668,291,ALG,ALLCAPS
+1669,292,Cameron,PER
+1670,292,realplayer,PER
+1671,292,Ovi,PER
+1672,292,Kudos,PER
+1673,292,fredrik,PER
+1674,292,Nokia,ORG
+1675,292,PDP,ALLCAPS
+1676,292,DNSNAT,ALLCAPS
+1677,292,ALG,ALLCAPS
+1678,292,NAT,ALLCAPS
+1679,292,IP,ALLCAPS
+1680,292,GUI,ALLCAPS
+1681,294,Nokias,ORG
+1682,295,Julien,PER
+1683,295,IPv Jari,PER
+1684,295,NAT,ALLCAPS
+1685,296,Jari,PER
+1686,296,APN,ALLCAPS
+1687,296,IP,ALLCAPS
+1688,297,anyone,PER
+1689,298,Mikael I,PER
+1690,298,Jari,PER
+1691,299,Dan Wing dwingciscocom,PER
+1692,299,ALG,ORG
+1693,299,IPv,ORG
+1694,299,AAAA,ALLCAPS
+1695,300,SmFyaSwNCgKPiAIFRoZXJlIGpZhIGJlIGFuIGltcGFjdCBvbiBaGUgUGsaWNIGFuZCBD,ORG
+1696,301,David Crowe,PER
+1697,301,Laganier Julien,PER
+1698,301,AM Laganier,ORG
+1699,301,DSL,ALLCAPS
+1700,302,SIPTO,ORG
+1701,302,GPPs,ORG
+1702,302,AAAA,ALLCAPS
+1703,302,PNAT,ALLCAPS
+1704,302,DNS,ALLCAPS
+1705,302,IP,ALLCAPS
+1706,303,US Embassy,ORG
+1707,303,VISA,ORG
+1708,304,Dan Wing dwingciscocom,PER
+1709,304,Tao Sun,PER
+1710,304,PNAT,ALLCAPS
+1711,304,WKP,ALLCAPS
+1712,304,IP,ALLCAPS
+1713,304,AAAA,ALLCAPS
+1714,304,our PNAT,ORG
+1715,304,China,LOC
+1716,306,GTP,ALLCAPS
+1717,306,TEID,ALLCAPS
+1718,306,GRE,ALLCAPS
+1719,306,APN,ALLCAPS
+1720,306,GPP,ALLCAPS
+1721,306,WAN,ALLCAPS
+1722,306,PDP,ALLCAPS
+1723,306,ISP,ALLCAPS
+1724,308,Teemu,PER
+1725,308,RFC,PER
+1726,308,DR,ALLCAPS
+1727,308,RR,ALLCAPS
+1728,308,DHCP,ALLCAPS
+1729,308,PD,ALLCAPS
+1730,308,PDP,ALLCAPS
+1731,308,WAN,ALLCAPS
+1732,308,ISP,ORG
+1733,309,Fredrik,PER
+1734,309,China Country,LOC
+1735,309,China,LOC
+1736,309,Hongkong,LOC
+1737,309,IP,ALLCAPS
+1738,310,IMHO,ORG
+1739,310,Google,ORG
+1740,310,NTT Global Crossing Hurricane Electric Time Warner Telecom,ORG
+1741,310,Baidu Yahoo Google Akamai,ORG
+1742,310,Facebook,ORG
+1743,310,Youtube,ORG
+1744,310,Akamai,PER
+1745,310,DS,ALLCAPS
+1746,310,CERNNET,ALLCAPS
+1747,311,DHCPv PD,PER
+1748,311,DHCPv,PER
+1749,311,RR,ALLCAPS
+1750,311,ISP,ALLCAPS
+1751,311,DR,ALLCAPS
+1752,311,WAN,ALLCAPS
+1753,311,GPP,ALLCAPS
+1754,311,NEMO,ALLCAPS
+1755,312,Teemu,PER
+1756,312,DHCPv,ORG
+1757,312,RR,ALLCAPS
+1758,312,ISP,ALLCAPS
+1759,312,DR,ALLCAPS
+1760,312,PD,ALLCAPS
+1761,312,WAN,ALLCAPS
+1762,312,GPP,ALLCAPS
+1763,312,NEMO,ALLCAPS
+1764,313,Sebastian,PER
+1765,314,Cameron,PER
+1766,314,NAT,ORG
+1767,314,IPvonly,ORG
+1768,314,DNS,ALLCAPS
+1769,316,ure,PER
+1770,316,Gary Jones,PER
+1771,316,Raj Patil,PER
+1772,316,IPvonly,ORG
+1773,316,TMobile,ORG
+1774,316,TMobile USA,ORG
+1775,316,Nokia,ORG
+1776,316,GPP,ALLCAPS
+1777,316,NAT,ALLCAPS
+1778,316,DNS,ALLCAPS
+1779,316,DS,ALLCAPS
+1780,316,APN,ALLCAPS
+1781,316,UE,ALLCAPS
+1782,316,PDP,ALLCAPS
+1783,316,VP,ALLCAPS
+1784,316,VERY,ALLCAPS
+1785,316,San Francisco,LOC
+1786,317,RFC,ALLCAPS
+1787,317,GPP,ALLCAPS
+1788,318,Hello Hui,PER
+1789,318,GPP,ALLCAPS
+1790,319,Julien,PER
+1791,319,Jouni,PER
+1792,319,AFs,ORG
+1793,319,Internet,ORG
+1794,319,IMS,ORG
+1795,319,NAT,ALLCAPS
+1796,319,PDN,ALLCAPS
+1797,319,PCC,ALLCAPS
+1798,320,Jouni,PER
+1799,320,Cameron,PER
+1800,320,one,PER
+1801,320,UE,ALLCAPS
+1802,320,ALG,ALLCAPS
+1803,320,AFTR,ALLCAPS
+1804,320,IP,ALLCAPS
+1805,320,RFCRFC,ALLCAPS
+1806,320,APN,ALLCAPS
+1807,321,Cameron,PER
+1808,321,oses,PER
+1809,322,Hi Jari,PER
+1810,323,Jouni,PER
+1811,323,UE,ALLCAPS
+1812,323,EPS,ALLCAPS
+1813,323,PDN,ALLCAPS
+1814,323,NAT,ALLCAPS
+1815,323,RFC,ALLCAPS
+1816,323,APN,ALLCAPS
+1817,323,APNPDN,ALLCAPS
+1818,323,EPC,ORG
+1819,323,OSes,ORG
+1820,324,Jouni,PER
+1821,324,UE,ALLCAPS
+1822,324,EPS,ALLCAPS
+1823,324,PDN,ALLCAPS
+1824,324,NAT,ALLCAPS
+1825,324,RFC,ALLCAPS
+1826,324,APN,ALLCAPS
+1827,324,APNPDN,ALLCAPS
+1828,324,EPC,ORG
+1829,324,OSes,ORG
+1830,325,Delegates,PER
+1831,325,secretary,PER
+1832,325,Jackie,PER
+1833,325,San Francisco,LOC
+1834,325,Nikko Ballroom,LOC
+1835,325,floor,LOC
+1836,325,the Nikko San Francisco Hotel,LOC
+1837,325,the Vista Room at the Hilton San Francisco The Vista Room,LOC
+1838,325,Vista level of Tower,LOC
+1839,325,Continental,ORG
+1840,325,China Mobile,ORG
+1841,325,ETSI,ORG
+1842,325,WLAN,ALLCAPS
+1843,326,TMobile USA,ORG
+1844,326,San Francisco,LOC
+1845,326,Cameron Byrne,PER
+1846,326,PDP,ALLCAPS
+1847,327,the,PER
+1848,327,SA,ORG
+1849,330,Fred,PER
+1850,330,Dave Thaler,PER
+1851,330,behavejabberietforg,PER
+1852,330,Spencer,PER
+1853,330,Fred Baker,PER
+1854,330,Bertenyi,PER
+1855,330,Frederick Baker messengerwebexcom,PER
+1856,330,Frederick Baker,PER
+1857,330,Balazs NSN HUBudapest,ORG
+1858,330,Cc gvietforg,ORG
+1859,330,messengerwebexcom,ORG
+1860,330,San Francisco,LOC
+1861,330,AM,ALLCAPS
+1862,330,PM,ALLCAPS
+1863,330,PST,ALLCAPS
+1864,330,GPPIETF,ALLCAPS
+1865,331,behavejabberietforgmailtobehavejabberietforg,PER
+1866,331,Behave chairs,PER
+1867,331,IETFGPP,ORG
+1868,332,IETF,ORG
+1869,333,Vista Room at the Hilton San Francisco The Vista Room,LOC
+1870,333,Vista level,LOC
+1871,333,Tower Hui Hui Deng denghuigmailcom,LOC
+1872,333,denghuigmailcom,DIG
+1873,334,Fred,PER
+1874,334,Spencer,PER
+1875,334,Fred Baker,PER
+1876,334,Bertenyi,PER
+1877,334,Frederick Baker messengerwebexcom,PER
+1878,334,Frederick Baker,PER
+1879,334,Balazs NSN HUBudapest Bertenyi,ORG
+1880,334,Cc gvietforg,ORG
+1881,334,messengerwebexcom,ORG
+1882,334,San Francisco,LOC
+1883,334,AM,ALLCAPS
+1884,334,PM,ALLCAPS
+1885,334,PST,ALLCAPS
+1886,334,GPPIETF,ALLCAPS
+1887,335,webex,DIG
+1888,339,DHCPv,ORG
+1889,339,DHCP,ORG
+1890,339,SLAAC,ORG
+1891,339,ID,ALLCAPS
+1892,339,PD,ALLCAPS
+1893,340,Conrad,PER
+1894,340,UE,PER
+1895,340,DR,PER
+1896,340,SLAAC,ORG
+1897,340,DHCPvlight,ORG
+1898,340,ISP,ALLCAPS
+1899,340,RR,ALLCAPS
+1900,342,Teemu,PER
+1901,342,teemusavolainennokiacom,PER
+1902,342,IMHO,ORG
+1903,342,SAM,ALLCAPS
+1904,342,IP,ALLCAPS
+1905,342,RD,ALLCAPS
+1906,342,GPP,ALLCAPS
+1907,342,PDP,ALLCAPS
+1908,342,WAN,ALLCAPS
+1909,342,ISP,ALLCAPS
+1910,342,Anaheim,LOC
+1911,343,WLAN,ALLCAPS
+1912,343,AC,ALLCAPS
+1913,343,CPE,ALLCAPS
+1914,344,Internet,MISC
+1915,344,WAN,ALLCAPS
+1916,345,AC,ORG
+1917,345,Mikael,PER
+1918,345,PCC,ALLCAPS
+1919,345,PPP,ALLCAPS
+1920,346,gv,PER
+1921,346,ipv,PER
+1922,346,EPC,ORG
+1923,346,UEThere,ORG
+1924,346,GPP,ORG
+1925,346,UE,ORG
+1926,346,MME,ORG
+1927,346,HSSAAA,ORG
+1928,346,ULDL,ORG
+1929,346,SGW,ORG
+1930,346,UEs,ORG
+1931,346,GSMAs,ORG
+1932,346,GSMA,ORG
+1933,346,PDNGW,ALLCAPS
+1934,346,PDN,ALLCAPS
+1935,346,PDP,ALLCAPS
+1936,346,AS,ALLCAPS
+1937,346,GPRS,ALLCAPS
+1938,347,enduser,PER
+1939,347,Querubin,PER
+1940,348,entity,PER
+1941,348,Jouni,PER
+1942,348,EPC,ORG
+1943,348,PDNGWs,ORG
+1944,348,PDNs,ORG
+1945,348,UEThere,ORG
+1946,348,PDNGW,ORG
+1947,348,HSSAAA,ORG
+1948,348,UE,ORG
+1949,348,SGW,ORG
+1950,348,UEs,ORG
+1951,348,GSMAs,ORG
+1952,348,GSMA,ORG
+1953,348,PDN,ALLCAPS
+1954,348,MME,ALLCAPS
+1955,348,IR,ALLCAPS
+1956,348,GPP,ALLCAPS
+1957,348,AS,ALLCAPS
+1958,348,GRX,ALLCAPS
+1959,348,IPX,ALLCAPS
+1960,350,Jabber,PER
+1961,350,DHCP,ORG
+1962,351,Anyone,PER
+1963,351,IP,ALLCAPS
+1964,352,IETFGPP,ORG
+1965,352,ML,ALLCAPS
+1966,353,Suresh,PER
+1967,353,a,PER
+1968,353,Zhenqiang Li,PER
+1969,353,IETF,ORG
+1970,353,DHCPvPD,ORG
+1971,353,Department of Network Technology China Mobile Research Institute,ORG
+1972,353,UE,ALLCAPS
+1973,353,GPP,ALLCAPS
+1974,354,Zhenqiang Li,PER
+1975,354,inline Suresh,PER
+1976,354,SLAAC,PER
+1977,354,IETF,ORG
+1978,354,PCC,ORG
+1979,354,GPP SA,ORG
+1980,354,UE,ALLCAPS
+1981,354,FB,ALLCAPS
+1982,354,PDN,ALLCAPS
+1983,354,DHCP,ALLCAPS
+1984,354,PD,ALLCAPS
+1985,354,APN,ALLCAPS
+1986,355,Zhenqiang,PER
+1987,355,GPP,ORG
+1988,356,ZhengqiangAA,PER
+1989,356,Frank,PER
+1990,356,vopsAA,PER
+1991,356,sureshkrishnanericssoncomA,PER
+1992,356,hrefDmailtolizhenqiangchinamobilecomlizhenqiang,PER
+1993,356,nanericssoncomsureshkrishnanericssoncomA,PER
+1994,356,Savolainen,PER
+1995,356,hrefDmailtodhcwgietforgdhcwgietforg,PER
+1996,356,hrefDmailtogvietforggvietfo,PER
+1997,356,GPP,ALLCAPS
+1998,356,UE,ALLCAPS
+1999,356,CN,ALLCAPS
+2000,356,AMA,ALLCAPS
+2001,356,EPC,ALLCAPS
+2002,356,IETF,ALLCAPS
+2003,356,UEA,ALLCAPS
+2004,356,toDmailtosureshkrishnanericssoncom,ORG
+2005,357,Frank,PER
+2006,357,PDs I,PER
+2007,357,R,PER
+2008,357,R R,PER
+2009,357,BABCFECCBABA,PER
+2010,357,Frank Brockners,PER
+2011,357,lizhenqiangchinamobilecom,PER
+2012,357,sureshkrishnanerics,PER
+2013,357,Zhenqiang Li,PER
+2014,357,Suresh,PER
+2015,357,UEs,ORG
+2016,357,Zhenqiang,ORG
+2017,357,Department of Network Technology China Mobile Research Institute BABCFECCBABA,ORG
+2018,357,Brockners,ORG
+2019,357,BACBCDCABBCEABA CADBCFECCBABA lizhenqiangchinamobilecom,ORG
+2020,357,BADCBCDABA younikorhonennsncom,ORG
+2021,357,DFCCEABA,ORG
+2022,357,GPP EPC,ORG
+2023,357,IETF,ORG
+2024,357,UE,ALLCAPS
+2025,357,GPP,ALLCAPS
+2026,357,APN,ALLCAPS
+2027,357,PDN,ALLCAPS
+2028,357,FB,ALLCAPS
+2029,357,SLAAC,ALLCAPS
+2030,357,DHCP,ALLCAPS
+2031,357,PD,ALLCAPS
+2032,357,PCC,ALLCAPS
+2033,357,SA,ALLCAPS
+2034,358,Behcet I,PER
+2035,358,Behcet,PER
+2036,358,BACBCDCABBCEABA,PER
+2037,358,CADBCFECCBABA,PER
+2038,358,lizhenqiangchinamobilecom,PER
+2039,358,BADCBCDABA gvietforg,PER
+2040,358,Zhengqiang,PER
+2041,358,Frank,PER
+2042,358,GPP,ORG
+2043,358,UE,ORG
+2044,358,Zhenqiang,ORG
+2045,358,Department of Network Technology China Mobile Research Institute BABCFECCBABA Behcet,ORG
+2046,358,gvietforg,ORG
+2047,358,GPP EPC,ORG
+2048,358,namobilecom,ORG
+2049,358,mobilecom,ORG
+2050,358,volainen gvietforg,ORG
+2051,358,DFCCEABA,ALLCAPS
+2052,358,CN,ALLCAPS
+2053,359,UE,ORG
+2054,359,RR,ORG
+2055,359,GPP,ORG
+2056,359,AR PGW,LOC
+2057,360,Zhenqiang,PER
+2058,360,Frank sureshkrishnanericssoncom,PER
+2059,360,Dhananjay,PER
+2060,360,gvietforg,ORG
+2061,360,LTE,ALLCAPS
+2062,360,UE,ALLCAPS
+2063,361,ND,PER
+2064,361,UE,ORG
+2065,361,UEs,ORG
+2066,361,NAT,ALLCAPS
+2067,361,APN,ALLCAPS
+2068,361,PDN,ALLCAPS
+2069,362,R,PER
+2070,362,Zhenqiang Li Department,PER
+2071,362,Frank Brockners,PER
+2072,362,Suresh,PER
+2073,362,of Network Technology China Mobile,ORG
+2074,362,lizhenqiangchinamobilecom,ORG
+2075,362,DFCCEABA,ORG
+2076,362,GPP EPC,ORG
+2077,362,SLAAC,ORG
+2078,362,DHCP,ORG
+2079,362,PCC,ORG
+2080,362,UE,ALLCAPS
+2081,362,PDN,ALLCAPS
+2082,362,PN,ALLCAPS
+2083,362,BACBCDCABBCEABA,ALLCAPS
+2084,362,CADBCFECCBABA,ALLCAPS
+2085,362,BADCBCDABA,ALLCAPS
+2086,362,FB,ALLCAPS
+2087,362,APN,ALLCAPS
+2088,362,PD,ALLCAPS
+2089,363,UE,ORG
+2090,363,PGW Xingyue ZTE Corporation,ORG
+2091,363,XY,ALLCAPS
+2092,363,APN,ALLCAPS
+2093,363,PDN,ALLCAPS
+2094,363,PD,ALLCAPS
+2095,364,UE,ORG
+2096,364,PGW Xingyue ZTE Corporation,ORG
+2097,364,XY,ALLCAPS
+2098,364,APN,ALLCAPS
+2099,364,PDN,ALLCAPS
+2100,364,PD,ALLCAPS
+2101,365,Frank,PER
+2102,365,S I,PER
+2103,365,Zhenqiang Li,PER
+2104,365,Zhenqiang,PER
+2105,365,GPP,ORG
+2106,365,Department of Network Technology China Mobile Research Institute,ORG
+2107,365,lizhenqiangchinamobilecom,ORG
+2108,365,sureshkrishnanericssoncom,ORG
+2109,365,dhcwgietforg gvietforg Dhananjay,ORG
+2110,365,GPP EPC,ORG
+2111,365,LTE,ALLCAPS
+2112,365,GPRS,ALLCAPS
+2113,365,APN,ALLCAPS
+2114,365,RE,ALLCAPS
+2115,366,Teemu I,PER
+2116,366,Zhenqiang Li,PER
+2117,366,BABCFECCBABA teemusavolainennokiacom,PER
+2118,366,BACBCDCABBCEABA CADBCFECCBABA fbrockneciscocom lizhenqiangchinamobilecom,PER
+2119,366,ureshkrishnanericssoncom,PER
+2120,366,younikorhonennsncom,PER
+2121,366,Teemu,PER
+2122,366,ricssoncom,PER
+2123,366,UE,ORG
+2124,366,Department of Network Technology China Mobile Research Institute,ORG
+2125,366,teemusavolainennokiacom,ORG
+2126,366,DFCCEABA,ALLCAPS
+2127,366,GPP,ALLCAPS
+2128,366,EPC,ALLCAPS
+2129,366,ND,ALLCAPS
+2130,366,NAT,ALLCAPS
+2131,366,APN,ALLCAPS
+2132,366,PDN,ALLCAPS
+2133,366,FFFFFFFFFFFFFFFFFFFFFFFF,ALLCAPS
+2134,367,S,PER
+2135,367,Zhenqiang Li Department,PER
+2136,367,Gundavelli,PER
+2137,367,lizhenqiangchinamobilecom Frank Brockners,PER
+2138,367,Dhananjay,PER
+2139,367,Zhenqiang Li,PER
+2140,367,Frank Brockners,PER
+2141,367,lizhenqiangchinamobilecom,PER
+2142,367,Suresh,PER
+2143,367,GPP,ORG
+2144,367,GGSN,ORG
+2145,367,PDNGW,ORG
+2146,367,of Network Technology China Mobile Research Institute,ORG
+2147,367,sureshkrishnanericssoncom,ORG
+2148,367,GPP EPC,ORG
+2149,367,Department of Network Technology China Mobile,ORG
+2150,367,PD,ALLCAPS
+2151,367,UE,ALLCAPS
+2152,367,PDN,ALLCAPS
+2153,367,RE,ALLCAPS
+2154,367,FB,ALLCAPS
+2155,367,SLAAC,ALLCAPS
+2156,367,DHCP,ALLCAPS
+2157,367,PCC,ALLCAPS
+2158,367,APN,ALLCAPS
+2159,368,Xingyue,PER
+2160,368,BABCFECCBABA zhouxingyueztecomcn,PER
+2161,368,BACBCDCABBCEABA CADBCFECCBABA,PER
+2162,368,gvietforg gvbouncesietforg,PER
+2163,368,ananjay Patki dhpatki Frank Brockners,PER
+2164,368,sureshkrishnaneric ssoncom,PER
+2165,368,wangzhihaiztecomcn,PER
+2166,368,zongzaifengztecomcn,PER
+2167,368,yingzhewuzteusacom,PER
+2168,368,DFCCEABA,PER
+2169,368,gvbouncesietforg,PER
+2170,368,UEs,ORG
+2171,368,PDNGW,ORG
+2172,368,Zhenqiang,ORG
+2173,368,Department of Network Technology China Mobile Research Institute BABCFECCBABA,ORG
+2174,368,zhouxingyueztecomcn,ORG
+2175,368,lizhenqiangchinamobilecom,ORG
+2176,368,younikorhonennsncom,ORG
+2177,368,DBDDA,ORG
+2178,368,PGW Xingyue,ORG
+2179,368,UE,ALLCAPS
+2180,368,APN,ALLCAPS
+2181,368,GPP,ALLCAPS
+2182,368,EPC,ALLCAPS
+2183,368,XY,ALLCAPS
+2184,368,PDN,ALLCAPS
+2185,368,PD,ALLCAPS
+2186,368,FFFFFFFFFFFFFFFFFFFFFFFF,ALLCAPS
+2187,369,UE,PER
+2188,369,NAT,ALLCAPS
+2189,370,CGA,ALLCAPS
+2190,371,IETF,ORG
+2191,371,France Telecom Group,ORG
+2192,371,GPP,ALLCAPS
+2193,372,Teemu I,PER
+2194,372,EPC,PER
+2195,372,la,ORG
+2196,372,de teemusavolainennokiacom,ORG
+2197,372,lizhenqiangchinamobilecom,ORG
+2198,372,fbrockneciscocom sureshkrishnanericssoncom,ORG
+2199,372,GPP EPC,ORG
+2200,372,UE,ALLCAPS
+2201,372,LAN,ALLCAPS
+2202,372,NAT,ALLCAPS
+2203,373,Teemu Fully,PER
+2204,373,Cheers Suresh,PER
+2205,373,IPv,DIG
+2206,374,Teemu,PER
+2207,374,lizhenqiangchinamobilecom,ORG
+2208,374,sureshkrishnanericssoncom,ORG
+2209,374,GPP EPC,ORG
+2210,374,UE,ALLCAPS
+2211,374,NAT,ALLCAPS
+2212,374,GPP,ALLCAPS
+2213,374,EPC,ALLCAPS
+2214,374,ND,ALLCAPS
+2215,375,LTE,ORG
+2216,375,IETF,ORG
+2217,375,IETFbased,ORG
+2218,375,GPP,ALLCAPS
+2219,375,BOF,ALLCAPS
+2220,376,Network,PER
+2221,376,Hussein AlBahadili,PER
+2222,376,hbahadiligmailcom,PER
+2223,376,Arab Academy for Banking Financial Sciences Jordan hbahadiligmailcom,ORG
+2224,376,Idea Group Inc wwwigiglobalcom,ORG
+2225,376,IGI,ALLCAPS
+2226,376,RF,ALLCAPS
+2227,376,TCP,ALLCAPS
+2228,377,Analysis,PER
+2229,377,Hussein AlBahadili,PER
+2230,377,hbahadiligmailcom,PER
+2231,377,Modeling,ORG
+2232,377,and,ORG
+2233,377,Arab Academy for Banking Financial Sciences Jordan hbahadiligmailcom,ORG
+2234,377,Idea Group Inc wwwigiglobalcom,ORG
+2235,377,IGI,ALLCAPS
+2236,377,RF,ALLCAPS
+2237,377,TCP,ALLCAPS
+2238,378,Hussein AlBahadili,PER
+2239,378,Arab Academy for Banking Financial Sciences Jordan hbahadiligmailcom hbahadiligmailcom Publisher IGI Global formerly Idea Group Inc wwwigiglobalcom,ORG
+2240,378,FINAL,ALLCAPS
+2241,378,CALL,ALLCAPS
+2242,378,FOR,ALLCAPS
+2243,378,CHAPTER,ALLCAPS
+2244,378,PROPOSAL,ALLCAPS
+2245,378,RF,ALLCAPS
+2246,378,TCP,ALLCAPS
+2247,378,IGI,ALLCAPS
+2248,379,LTE,ALLCAPS
+2249,381,Scott Sent,PER
+2250,381,GSMS,ORG
+2251,381,GSMA,ORG
+2252,381,IETF,ORG
+2253,381,Shanghai,LOC
+2254,382,er,PER
+2255,382,GSMAs,ORG
+2256,382,LTE,ALLCAPS
+2257,383,Cameron you,PER
+2258,383,my mobile,PER
+2259,384,the,PER
+2260,384,RIPE,ORG
+2261,384,APNIC,ORG
+2262,384,NATDNS,ALLCAPS
+2263,386,Forward,ORG
+2264,386,RomanArceaorangemd,ORG
+2265,387,APNIC AsiaPac,ORG
+2266,387,RIPE,ALLCAPS
+2267,388,Ahmed,PER
+2268,388,IETF,ORG
+2269,389,TR,ALLCAPS
+2270,389,TSP,ALLCAPS
+2271,389,RFC,ALLCAPS
+2272,390,GPP,ORG
+2273,390,GPRSEPC,ORG
+2274,390,DSLite,ORG
+2275,390,IETF,ORG
+2276,390,GIDSLite,ORG
+2277,390,CGN,ORG
+2278,390,GTP,ALLCAPS
+2279,391,Hui,PER
+2280,391,UE,ORG
+2281,391,CGN Mobile,ORG
+2282,391,PMIPvGTP,ORG
+2283,391,CGN,ORG
+2284,391,DS,ALLCAPS
+2285,391,IP,ALLCAPS
+2286,392,DSLite,ORG
+2287,392,IETF,ORG
+2288,392,NATDNS,ALLCAPS
+2289,393,DSlite,ORG
+2290,393,Envoyé,ORG
+2291,393,gvietforg,ORG
+2292,393,DSLite,ORG
+2293,393,IETF,ORG
+2294,393,IPvonly,ORG
+2295,393,PCC,PER
+2296,393,Hope,PER
+2297,393,Julien De gvbouncesietforg mailtogvbouncesietforg De la part de Ahmed AbuAbed,PER
+2298,393,Hui,PER
+2299,393,TS,ALLCAPS
+2300,393,NATDNS,ALLCAPS
+2301,394,Alaa H AlHamami Amman Arab,PER
+2302,394,Ghossoon,PER
+2303,394,Emailthreatcounteryahoocouk,PER
+2304,394,IGI Global wwwigiglobalcom,ORG
+2305,394,IGIbook and Association,ORG
+2306,394,IGIbook,ORG
+2307,394,threatcounteryahoocouk,ORG
+2308,394,University Jordan P O Box Amman Jordan,ORG
+2309,394,MW AlSadoon Applied Sciences University Bahrain POB Villa Road Block Juffair,ORG
+2310,394,IGI,MISC
+2311,395,Juguetitos,PER
+2312,397,Hemant,PER
+2313,397,TS,ALLCAPS
+2314,397,RTP,ALLCAPS
diff --git a/pyproject.toml b/pyproject.toml
index 5e68276..03aff0a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -38,6 +38,10 @@ dependencies = [
"nbconvert",
"validator-collection",
"markdown",
+ "spacy",
+ "transformers[torch]",
+ "contractions",
+ "email_reply_parser",
"notebook",
"click"
]