regression.msmarco-v1-passage.doc2query.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-passage-doc2query
corpus_path: collections/msmarco/passage-expanded-topk10/

index_path: indexes/lucene-inverted.msmarco-v1-passage.doc2query/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 9
index_options: -storePositions -storeDocvectors -storeRaw
index_stats:
  documents: 8841823
  documents (non-empty): 8841823
  total terms: 739691803

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@10
    command: bin/trec_eval
    params: -c -M 10 -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 Passage: Dev](https://github.com/microsoft/MSMARCO-Passage-Ranking)"
    id: dev
    path: topics.msmarco-passage.dev-subset.txt
    qrel: qrels.msmarco-passage.dev-subset.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25
    results:
      AP@1000:
        - 0.2270
      RR@10:
        - 0.2189
      R@100:
        - 0.7133
      R@1000:
        - 0.8900
# PRF regressions are no longer maintained for sparse judgments to reduce running times.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
#    results:
#      AP@1000:
#        - 0.2030
#      RR@10:
#        - 0.1941
#      R@100:
#        - 0.7003
#      R@1000:
#        - 0.8909
  - name: bm25-tuned
    display: BM25 (tuned)
    params: -bm25 -bm25.k1 0.82 -bm25.b 0.68
    results:
      AP@1000:
        - 0.2293
      RR@10:
        - 0.2213
      R@100:
        - 0.7171
      R@1000:
        - 0.8911
# PRF regressions are no longer maintained for sparse judgments to reduce running times.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 0.82 -bm25.b 0.68 -rm3
#    results:
#      AP@1000:
#        - 0.2081
#      RR@10:
#        - 0.1992
#      R@100:
#        - 0.7051
#      R@1000:
#        - 0.8946