All Downloads are FREE. Search and download functionalities are using the official Maven repository.

regression.dl19-doc-segmented-unicoil-noexp.yaml Maven / Gradle / Ivy

---
corpus: msmarco-doc-segmented-unicoil-noexp
corpus_path: collections/msmarco/msmarco-doc-segmented-unicoil-noexp/

download_url: https://rgw.cs.uwaterloo.ca/JIMMYLIN-bucket0/data/msmarco-doc-segmented-unicoil-noexp.tar
download_checksum: 11b226e1cacd9c8ae0a660fd14cdd710

index_path: indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/
collection_class: JsonVectorCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -impact -pretokenized -storeDocvectors
index_stats:
  documents: 20545677
  documents (non-empty): 20545677
  total terms: 152323732876

metrics:
  - metric: AP@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -M 100 -m map # Note, this is different DL 2019 passage ranking!
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: nDCG@10
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m ndcg_cut.10
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m recall.1000
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topic_root: src/main/resources/topics-and-qrels/
qrels_root: src/main/resources/topics-and-qrels/
topics:
  - name: "[DL19 (Doc)](https://trec.nist.gov/data/deep2019.html)"
    id: dl19
    path: topics.dl19-doc.unicoil-noexp.0shot.tsv.gz
    qrel: qrels.dl19-doc.txt

models:
  - name: unicoil
    display: uniCOIL (no expansions)
    params: -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.2665
      nDCG@10:
        - 0.6349
      R@100:
        - 0.3943
      R@1000:
        - 0.6391
  - name: rm3
    display: +RM3
    params: -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.2936
      nDCG@10:
        - 0.6166
      R@100:
        - 0.4347
      R@1000:
        - 0.6909
  - name: rocchio
    display: +Rocchio
    params: -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.2959
      nDCG@10:
        - 0.6175
      R@100:
        - 0.4362
      R@1000:
        - 0.6979




© 2015 - 2025 Weber Informatics LLC | Privacy Policy