fever.yaml

---
corpus: fever
corpus_path: collections/fever/wiki-pages/

index_path: indexes/lucene-index.fever-paragraph/
collection_class: FeverParagraphCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 1
index_options: -storePositions -storeDocvectors -storeRaw
index_stats:
  documents: 5396106
  documents (non-empty): 5396060
  total terms: 322660819

metrics:
  - metric: R@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: true
  - metric: R@1000
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m recall.1000
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: true

topic_reader: TsvInt
topic_root: src/main/resources/topics-and-qrels/
qrels_root: src/main/resources/topics-and-qrels/
topics:
  - name: "[FEVER Paper Development Dataset](https://s3-eu-west-1.amazonaws.com/fever.public/paper_dev.jsonl)"
    id: dev
    path: topics.fever.dev.txt
    qrel: qrels.fever.dev.txt

models:
  - name: bm25-default
    display: BM25 (Default)
    params: -bm25
    results:
      R@100:
        - 0.8974
      R@1000:
        - 0.9477
  - name: bm25-tuned
    display: BM25 (Tuned)
    params: -bm25 -bm25.k1 0.9 -bm25.b 0.1
    results:
      R@100:
        - 0.8988
      R@1000:
        - 0.9481