regression.msmarco-doc-hgf-wp.yaml Maven / Gradle / Ivy

Go to download
---
corpus: msmarco-doc
corpus_path: collections/msmarco/msmarco-doc/

index_path: indexes/lucene-index.msmarco-doc-hgf-wp/
collection_class: JsonCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 7
index_options: -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased
index_stats:
  documents: 3213835
  documents (non-empty): 3213835
  total terms: 5326253111

metrics:
  - metric: AP@1000
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -m map
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: RR@100
    command: tools/eval/trec_eval.9.0.4/trec_eval
    params: -c -M 100 -m recip_rank
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - 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: false
  - 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: false

topic_reader: TsvInt
topic_root: src/main/resources/topics-and-qrels/
qrels_root: src/main/resources/topics-and-qrels/
topics:
  - name: "[MS MARCO Doc: Dev](https://github.com/microsoft/MSMARCO-Document-Ranking)"
    id: dev
    path: topics.msmarco-doc.dev.txt
    qrel: qrels.msmarco-doc.dev.txt

models:
  - name: bm25-default
    display: BM25 (default)
    params: -bm25 -analyzeWithHuggingFaceTokenizer  bert-base-uncased
    results:
      AP@1000:
        - 0.2234
      RR@100:
        - 0.2227
      R@100:
        - 0.7031
      R@1000:
        - 0.8743