regression.dl20-doc-segmented-docTTTTTquery.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-doc-segmented-docTTTTTquery
corpus_path: collections/msmarco/msmarco-doc-segmented-docTTTTTquery/

index_path: indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -storePositions -storeDocvectors -storeRaw
index_stats:
  documents: 20545677
  documents (non-empty): 20545677
  total terms: 4206646183

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 2020 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: "[DL20 (Doc)](https://trec.nist.gov/data/deep2020.html)"
    id: dl20
    path: topics.dl20.txt
    qrel: qrels.dl20-doc.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4150
      nDCG@10:
        - 0.5957
      R@100:
        - 0.6201
      R@1000:
        - 0.8046
  - name: bm25-default+rm3
    display: +RM3
    params: -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4271
      nDCG@10:
        - 0.5851
      R@100:
        - 0.6442
      R@1000:
        - 0.8266
  - name: bm25-default+rocchio
    display: +Rocchio
    params: -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4297
      nDCG@10:
        - 0.5873
      R@100:
        - 0.6475
      R@1000:
        - 0.8365
  - name: bm25-tuned
    display: BM25 (tuned)
    params: -bm25 -bm25.k1 2.56 -bm25.b 0.59 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4047
      nDCG@10:
        - 0.5943
      R@100:
        - 0.6195
      R@1000:
        - 0.7968
  - name: bm25-tuned+rm3
    display: +RM3
    params: -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4016
      nDCG@10:
        - 0.5711
      R@100:
        - 0.6383
      R@1000:
        - 0.8156
  - name: bm25-tuned+rocchio
    display: +Rocchio
    params: -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@100:
        - 0.4084
      nDCG@10:
        - 0.5809
      R@100:
        - 0.6432
      R@1000:
        - 0.8233