ciral-v1.0-sw-en.yaml

---
corpus: ciral-swahili-english
corpus_path: collections/ciral/ciral-passages-swahili-english/

index_path: indexes/lucene-index.ciral-v1.0-sw-en/
collection_class: MrTyDiCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -storePositions -storeDocvectors -storeRaw
index_stats:
  documents: 949013
  documents (non-empty): 949013
  total terms: 83817100

metrics:
  - metric: nDCG@20
    command: target/appassembler/bin/trec_eval
    params: -c -m ndcg_cut.20
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: target/appassembler/bin/trec_eval
    params: -c -m recall.100
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topics:
  - name: "[CIRAL Swahili: Test Set A (Shallow Judgements)](https://huggingface.co/datasets/CIRAL/ciral)"
    id: test-a-shallow
    path: topics.ciral-v1.0-sw-test-a.tsv
    qrel: qrels.ciral-v1.0-sw-test-a.tsv
  - name: "[CIRAL Swahili: Test Set A (Pools)](https://huggingface.co/datasets/CIRAL/ciral)"
    id: test-a-pools
    path: topics.ciral-v1.0-sw-test-a.tsv
    qrel: qrels.ciral-v1.0-sw-test-a-pools.tsv
  - name: "[CIRAL Swahili: Test Set B](https://huggingface.co/datasets/CIRAL/ciral)"
    id: test-b-shallow
    path: topics.ciral-v1.0-sw-test-b.tsv
    qrel: qrels.ciral-v1.0-sw-test-b.tsv

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25 -hits 1000
    results:
      nDCG@20:
        - 0.2033
        - 0.2327
        - 0.2582
      R@100:
        - 0.4786
        - 0.3636
        - 0.4918