msmarco-doc-docTTTTTquery-per-doc.yaml

---
name: msmarco-doc-docTTTTTquery-per-doc
index_command: target/appassembler/bin/IndexCollection
index_utils_command: target/appassembler/bin/IndexReaderUtils
search_command: target/appassembler/bin/SearchCollection
topic_root: src/main/resources/topics-and-qrels/
qrels_root: src/main/resources/topics-and-qrels/
index_root:
ranking_root:
collection: JsonCollection
generator: DefaultLuceneDocumentGenerator
threads: 1
index_options:
  - -storePositions
  - -storeDocvectors
  - -storeRaw
topic_reader: TsvInt
evals:
  - command: tools/eval/trec_eval.9.0.4/trec_eval
    params:
      - -m map
      - -c
    separator: "\t"
    parse_index: 2
    metric: map
    metric_precision: 4
    can_combine: true
  - command: tools/eval/trec_eval.9.0.4/trec_eval
    params:
      - -m recall.1000
      - -c
    separator: "\t"
    parse_index: 2
    metric: R@1000
    metric_precision: 4
    can_combine: true
input_roots:
  - /tuna1/      # on tuna
  - /store/      # on orca
  - /scratch2/   # on damiano
input: collections/msmarco/doc-docTTTTTquery-per-doc
index_path: indexes/lucene-index.msmarco-doc-docTTTTTquery-per-doc.pos+docvectors+raw
index_stats:
  documents: 3213834
  documents (non-empty): 3213834
  total terms: 3748332076
topics:
  - name: "[MS MARCO Document Ranking: Dev Queries](https://github.com/microsoft/MSMARCO-Document-Ranking)"
    path: topics.msmarco-doc.dev.txt
    qrel: qrels.msmarco-doc.dev.txt
models:
  - name: bm25-default
    display: BM25 (Default)
    params:
      - -bm25
    results:
      map:
        - 0.2886
      R@1000:
        - 0.9259