regression.msmarco-v1-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-inverted.msmarco-v1-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@1000
    command: bin/trec_eval
    params: -c -m map
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: RR@100
    command: bin/trec_eval
    params: -c -M 100 -m recip_rank
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: bin/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: bin/trec_eval
    params: -c -m recall.1000
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topics:
  - name: "[MS MARCO Doc: Dev](https://github.com/microsoft/MSMARCO-Document-Ranking)"
    id: dev
    path: topics.msmarco-doc.dev.txt
    qrel: qrels.msmarco-doc.dev.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
    results:
      AP@1000:
        - 0.3184
      RR@100:
        - 0.3179
      R@100:
        - 0.8479
      R@1000:
        - 0.9490
# PRF regressions are no longer maintained for sparse judgments to reduce running times.
# (commenting out instead of removing; in case these numbers are needed, just uncomment and rerun.)
#
#  - name: bm25-default+rm3
#    display: +RM3
#    params: -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
#    results:
#      AP@1000:
#        - 0.2808
#      RR@100:
#        - 0.2803
#      R@100:
#        - 0.8477
#      R@1000:
#        - 0.9551
#  - name: bm25-default+rocchio
#    display: +Rocchio
#    params: -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
#    results:
#      AP@1000:
#        - 0.2846
#      RR@100:
#        - 0.2841
#      R@100:
#        - 0.8479
#      R@1000:
#        - 0.9551
  - 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@1000:
        - 0.3213
      RR@100:
        - 0.3209
      R@100:
        - 0.8627
      R@1000:
        - 0.9530
# PRF regressions are no longer maintained for sparse judgments to reduce running times.
# (commenting out instead of removing; in case these numbers are needed, just uncomment and rerun.)
#
#  - 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@1000:
#        - 0.2978
#      RR@100:
#        - 0.2973
#      R@100:
#        - 0.8573
#      R@1000:
#        - 0.9563
#  - 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@1000:
#        - 0.2998
#      RR@100:
#        - 0.2994
#      R@100:
#        - 0.8600
#      R@1000:
#        - 0.9571