dl20-passage.unicoil.yaml

---
corpus: msmarco-passage-unicoil
corpus_path: collections/msmarco/msmarco-passage-unicoil/

download_url: https://rgw.cs.uwaterloo.ca/JIMMYLIN-bucket0/data/msmarco-passage-unicoil.tar
download_checksum: 78eef752c78c8691f7d61600ceed306f

index_path: indexes/lucene-inverted.msmarco-v1-passage.unicoil/
collection_class: JsonVectorCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -impact -pretokenized -storeDocvectors
index_stats:
  documents: 8841823
  documents (non-empty): 8841823
  total terms: 44495093768

metrics:
  - metric: AP@1000
    command: bin/trec_eval
    params: -m map -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: nDCG@10
    command: bin/trec_eval
    params: -m ndcg_cut.10 -c
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@100
    command: bin/trec_eval
    params: -m recall.100 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false
  - metric: R@1000
    command: bin/trec_eval
    params: -m recall.1000 -c -l 2
    separator: "\t"
    parse_index: 2
    metric_precision: 4
    can_combine: false

topic_reader: TsvInt
topics:
  - name: "[DL20 (Passage)](https://trec.nist.gov/data/deep2020.html)"
    id: dl20
    path: topics.dl20.unicoil.0shot.tsv.gz
    qrel: qrels.dl20-passage.txt

models:
  - name: unicoil-cached_q
    display: uniCOIL (with doc2query-T5 expansions)
    params: -impact -pretokenized
    results:
      AP@1000:
        - 0.4430
      nDCG@10:
        - 0.6745
      R@100:
        - 0.7006
      R@1000:
        - 0.8430
  - name: unicoil-cached_q+rm3
    display: +RM3
    params: -impact -pretokenized -rm3
    results:
      AP@1000:
        - 0.4478
      nDCG@10:
        - 0.6497
      R@100:
        - 0.6822
      R@1000:
        - 0.8417
  - name: unicoil-cached_q+rocchio
    display: +Rocchio
    params: -impact -pretokenized -rocchio
    results:
      AP@1000:
        - 0.4539
      nDCG@10:
        - 0.6599
      R@100:
        - 0.7096
      R@1000:
        - 0.8610