dl20-passage.wp-hgf.yaml

---
corpus: msmarco-passage
corpus_path: collections/msmarco/passage

index_path: indexes/lucene-inverted.msmarco-v1-passage.wp-hgf/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 9
index_options: -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased
index_stats:
  documents: 8841823
  documents (non-empty): 8841823
  total terms: 662900376

metrics:
  - metric: AP@1000
    command: bin/trec_eval
    params: -m map -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: nDCG@10
    command: bin/trec_eval
    params: -m ndcg_cut.10 -c
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: bin/trec_eval
    params: -m recall.100 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: bin/trec_eval
    params: -m recall.1000 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topics:
  - name: "[DL20 (Passage)](https://trec.nist.gov/data/deep2020.html)"
    id: dl20
    path: topics.dl20.txt
    qrel: qrels.dl20-passage.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased
    results:
      AP@1000:
        - 0.2606
      nDCG@10:
        - 0.4680
      R@100:
        - 0.5222
      R@1000:
        - 0.7633