wiki-all-6-3-tamber-bm25.yaml

---
corpus: wiki-all-6-3-tamber
corpus_path: collections/wikipedia/wiki-all-6-3-tamber

index_path: indexes/lucene-index.wiki-all-6-3-tamber/
collection_class: MrTyDiCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 20
index_options: -storeRaw
index_stats:
  documents: 76680040
  documents (non-empty): 76680037
  total terms: 5064706668

conversions:  
  - command: python -m pyserini.eval.convert_trec_run_to_dpr_retrieval_run
    params:  --combine-title-text
    in_file_ext: "" 
    out_file_ext: .json

metrics:
  - metric: top_20_accuracy
    command: python -m pyserini.eval.evaluate_dpr_retrieval
    params:  --topk 20 --retrieval
    separator: " "
    parse_index: 1
    metric_precision: 4
    can_combine: false
  - metric: top_100_accuracy
    command: python -m pyserini.eval.evaluate_dpr_retrieval
    params:  --topk 100 --retrieval
    separator: " "
    parse_index: 1
    metric_precision: 4
    can_combine: false
    
topics:
  - name: "[DPR: Natural Questions Test](https://github.com/facebookresearch/DPR)"
    id: dpr-nq-test
    path: topics.dpr.nq.test.txt
    topic_reader: DprNq
  - name: "[DPR: TriviaQA Test](https://github.com/facebookresearch/DPR)"
    id: dpr-trivia-test
    path: topics.dpr.trivia.test.txt
    topic_reader: DprNq
  - name: "[DPR: SQuAD Test](https://github.com/facebookresearch/DPR)"
    id: dpr-squad-test
    path: topics.dpr.squad.test.txt
    topic_reader: DprJsonl
  - name: "[DPR: WebQuestions Test](https://github.com/facebookresearch/DPR)"
    id: dpr-wq-test
    path: topics.dpr.wq.test.txt
    topic_reader: DprJsonl
  - name: "[DPR: CuratedTREC Test](https://github.com/facebookresearch/DPR)"
    id: dpr-curated-test
    path: topics.dpr.curated.test.txt
    topic_reader: DprJsonl
    convert_params: --regex
  - name: "[EfficientQA: Natural Questions Test](https://efficientqa.github.io/)"
    id: nq-test
    path: topics.nq.test.txt
    topic_reader: DprNq

models:
  - name: bm25
    display: BM25 (default parameters)
    params: -bm25
    results:
      top_20_accuracy:
        - 0.6604
        - 0.7832
        - 0.7265
        - 0.6403
        - 0.8055
        - 0.6665
      top_100_accuracy:
        - 0.8083
        - 0.8482
        - 0.8325
        - 0.7874
        - 0.9135
        - 0.8166