Merge pull request #670 from nitishgupta/master

BasicTextAnnotationBuilder function for pre-tokenized text with cogcomp-nlpy
CogComp · Jul 23, 2018 · cd8ac71 · cd8ac71
2 parents 7066e7e + 15ff023
commit cd8ac71
Show file tree

Hide file tree

Showing 33 changed files with 154 additions and 148 deletions.
diff --git a/big-data-utils/pom.xml b/big-data-utils/pom.xml
@@ -3,7 +3,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <modelVersion>4.0.0</modelVersion>
@@ -23,7 +23,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>org.xeustechnologies.google-api</groupId>

diff --git a/chunker/pom.xml b/chunker/pom.xml
@@ -2,7 +2,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <modelVersion>4.0.0</modelVersion>
@@ -13,7 +13,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
 
         <dependency>
@@ -24,12 +24,12 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>LBJava-NLP-tools</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-pos</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>

diff --git a/commasrl/pom.xml b/commasrl/pom.xml
@@ -4,7 +4,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 
@@ -35,48 +35,48 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
             <optional>true</optional>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-curator</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-tokenizer</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-corpusreaders</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-inference</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>stanford_3.3.1</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-pos</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-ner</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-chunker</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>

diff --git a/core-utilities/pom.xml b/core-utilities/pom.xml
@@ -6,7 +6,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <artifactId>illinois-core-utilities</artifactId>

diff --git a/...tilities/src/main/java/edu/illinois/cs/cogcomp/annotation/BasicTextAnnotationBuilder.java b/...tilities/src/main/java/edu/illinois/cs/cogcomp/annotation/BasicTextAnnotationBuilder.java
@@ -43,20 +43,26 @@ public static TextAnnotation createTextAnnotationFromTokens(List<String[]> token
 
 
     /**
-     * The default way to create a {@link TextAnnotation} from pre-tokenized text.
+     * A way to create a {@link TextAnnotation} from pre-tokenized text from Python
      *
-     * @param tokenizedSentences A list of sentences, each one being an array of tokens
+     * @param tokenizedSentences A list of sentences, each one being an list of tokens
      * @return A {@link TextAnnotation} containing the SENTENCE and TOKENS views.
      */
-    public static TextAnnotation createTextAnnotationFromListofListofTokens(List<List<String>> tokenizedSentences) {
-        // Function name is not createTextAnnotationFromTokens - due to same erasure error
+    public static TextAnnotation createTextAnnotationFromListofListofTokens(List<List<Object>> tokenizedSentences) {
+        // This function takes List<List<Object>> to be able to run with cogcomp-nlpy (using pyjnius)
         // Convert the inner lists to String arrays
         // Call the default TextAnnotation builder function
+
         List<String[]> tokenizedSentences_formatted = new ArrayList<String[]>();
 
         // Converting inner list to array
-        for (List<String> sentence : tokenizedSentences) {
-            String[] sentence_array = (String[]) sentence.toArray();
+        for (List<Object> sentence : tokenizedSentences) {
+            String[] sentence_array = new String[sentence.size()];
+            int token_idx = 0;
+            for (Object w : sentence) {
+                sentence_array[token_idx] = (String) w;
+                token_idx += 1;
+            }
             tokenizedSentences_formatted.add(sentence_array);
         }
 

diff --git a/corpusreaders/pom.xml b/corpusreaders/pom.xml
@@ -6,7 +6,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <artifactId>illinois-corpusreaders</artifactId>
@@ -15,12 +15,12 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-tokenizer</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>org.slf4j</groupId>

diff --git a/curator/pom.xml b/curator/pom.xml
@@ -7,7 +7,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <artifactId>illinois-curator</artifactId>
@@ -16,7 +16,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
 
         <!-- Curator-related dependencies -->

diff --git a/dataless-classifier/pom.xml b/dataless-classifier/pom.xml
@@ -3,7 +3,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <modelVersion>4.0.0</modelVersion>
@@ -21,12 +21,12 @@
     	<dependency>
       		<groupId>edu.illinois.cs.cogcomp</groupId>
       		<artifactId>illinois-core-utilities</artifactId>
-      		<version>4.0.8</version>
+      		<version>4.0.9</version>
       	</dependency>
       	<dependency>
       		<groupId>edu.illinois.cs.cogcomp</groupId>
       		<artifactId>illinois-tokenizer</artifactId>
-      		<version>4.0.8</version>
+      		<version>4.0.9</version>
       	</dependency>
 		<dependency>
 			<groupId>org.slf4j</groupId>

diff --git a/depparse/pom.xml b/depparse/pom.xml
@@ -7,7 +7,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <artifactId>illinois-depparse</artifactId>
@@ -16,27 +16,27 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-edison</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-lemmatizer</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-pos</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-chunker</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
 
         <dependency>

diff --git a/edison/pom.xml b/edison/pom.xml
@@ -7,7 +7,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
     </parent>
 
     <artifactId>illinois-edison</artifactId>
@@ -16,7 +16,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <!--<dependency>-->
         <!--<groupId>edu.illinois.cs.cogcomp.resources</groupId>-->
@@ -80,13 +80,13 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-corpusreaders</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <!-- Used only in utilities.CreateTestTAResource -->
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-curator</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
             <scope>test</scope>
         </dependency>
         <dependency>

diff --git a/external/clausie/pom.xml b/external/clausie/pom.xml
@@ -5,7 +5,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
         <relativePath>../../pom.xml</relativePath>
     </parent>
 
@@ -24,7 +24,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>external-commons</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>org.slf4j</groupId>

diff --git a/external/external-commons/pom.xml b/external/external-commons/pom.xml
@@ -2,7 +2,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
         <relativePath>../../pom.xml</relativePath>
     </parent>
 
@@ -16,12 +16,12 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-tokenizer</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>org.cogcomp</groupId>

diff --git a/external/path-lstm/pom.xml b/external/path-lstm/pom.xml
@@ -2,7 +2,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
         <relativePath>../../pom.xml</relativePath>
     </parent>
 
@@ -16,12 +16,12 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>external-commons</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-edison</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <dependency>
             <groupId>org.cogcomp</groupId>

diff --git a/external/stanford_3.3.1/pom.xml b/external/stanford_3.3.1/pom.xml
@@ -5,7 +5,7 @@
     <parent>
         <artifactId>illinois-cogcomp-nlp</artifactId>
         <groupId>edu.illinois.cs.cogcomp</groupId>
-        <version>4.0.8</version>
+        <version>4.0.9</version>
         <relativePath>../../pom.xml</relativePath>
     </parent>
 
@@ -19,7 +19,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-core-utilities</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
         <!-- Stanford Core NLP, used for its parser (for SRL) -->
         <dependency>
@@ -36,7 +36,7 @@
         <dependency>
             <groupId>edu.illinois.cs.cogcomp</groupId>
             <artifactId>illinois-corpusreaders</artifactId>
-            <version>4.0.8</version>
+            <version>4.0.9</version>
         </dependency>
     </dependencies>
 </project>