wikipedia-dpr-100w-bm25.yaml

---
corpus: wikipedia-dpr-100w
corpus_path: collections/wikipedia/wikipedia-dpr-100w

index_path: indexes/lucene-index.wikipedia-dpr-100w/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 43
index_options: -storeRaw
index_stats:
  documents: 21015324
  documents (non-empty): 21015324
  total terms: 1512973244

conversions:  
  - command: python -m pyserini.eval.convert_trec_run_to_dpr_retrieval_run
    params: 
    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:
        - 0.6294
        - 0.7641
        - 0.7109
        - 0.6240
        - 0.8069
        - 0.6399
      top_100_accuracy:
        - 0.7825
        - 0.8315
        - 0.8184
        - 0.7549
        - 0.8991
        - 0.7922