regression.rag24-doc-segmented-test.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-v2.1-doc-segmented
corpus_path: collections/msmarco/msmarco_v2.1_doc_segmented/

index_path: indexes/lucene-inverted.msmarco-v2.1-doc-segmented/
collection_class: MsMarcoV2DocCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 24
index_options: -storeRaw
index_stats:
  documents: 113520750
  documents (non-empty): 113520750
  total terms: 22707699649

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

topic_reader: TsvString
topics:
  - name: "RAG 24: Test queries"
    id: rag24.test
    path: topics.rag24.test.txt
    qrel: qrels.rag24.test-umbrela-all.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25
    results:
      nDCG@20:
        - 0.3198
      nDCG@100:
        - 0.2563
      R@100:
        - 0.1395
  - name: bm25-default+rm3
    display: +RM3
    params: -bm25 -rm3 -collection MsMarcoV2DocCollection
    results:
      nDCG@20:
        - 0.3063
      nDCG@100:
        - 0.2410
      R@100:
        - 0.1318
  - name: bm25-default+rocchio
    display: +Rocchio
    params: -bm25 -rocchio -collection MsMarcoV2DocCollection
    results:
      nDCG@20:
        - 0.3196
      nDCG@100:
        - 0.2527
      R@100:
        - 0.1384