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

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

index_path: indexes/lucene-inverted.msmarco-v1-doc-segmented.wp-ca/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer
index_stats:
  documents: 20545677
  documents (non-empty): 20545677
  total terms: 9539433626

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 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer
    results:
      AP@1000:
        - 0.2787
      RR@100:
        - 0.2781
      R@100:
        - 0.7990
      R@1000:
        - 0.9286