regression.msmarco-v1-passage.wp-ca.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-passage
corpus_path: collections/msmarco/passage

index_path: indexes/lucene-inverted.msmarco-v1-passage.wp-ca/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 9
index_options: -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer
index_stats:
  documents: 8841823
  documents (non-empty): 8841823
  total terms: 1015216415

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 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer
    results:
      AP@1000:
        - 0.1968
      RR@10:
        - 0.1881
      R@100:
        - 0.6623
      R@1000:
        - 0.8607