regression.dl21-doc-segmented-unicoil-noexp-0shot.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-v2-doc-segmented-unicoil-noexp-0shot
corpus_path: collections/msmarco/msmarco_v2_doc_segmented_unicoil_noexp_0shot/

download_url: https://rgw.cs.uwaterloo.ca/JIMMYLIN-bucket0/data/msmarco_v2_doc_segmented_unicoil_noexp_0shot.tar
download_checksum: 28261587d6afde56efd8df4f950e7fb4
download_corpus: msmarco_v2_doc_segmented_unicoil_noexp_0shot

index_path: indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/
collection_class: JsonVectorCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 24
index_options: -impact -pretokenized
index_stats:
  documents: 124131404
  documents (non-empty): 124131404
  total terms: 805830282591

metrics:
  - metric: MAP@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -M 100 -m map
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: no
  - metric: MRR@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -M 100 -m recip_rank
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: true
  - 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: true
  - 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: "[DL21 (Doc)](https://microsoft.github.io/msmarco/TREC-Deep-Learning)"
    id: dl21
    path: topics.dl21.unicoil-noexp.0shot.tsv.gz
    qrel: qrels.dl21-doc.txt

models:
  - name: unicoil-noexp-0shot
    display: uniCOIL (noexp) zero-shot
    params: -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized
    results:
      MAP@100:
        - 0.2475
      MRR@100:
        - 0.9122
      nDCG@10:
        - 0.6282
      R@100:
        - 0.3497
      R@1000:
        - 0.6767