backgroundlinking20.yaml

---
name: backgroundlinking20
index_command: target/appassembler/bin/IndexCollection
index_utils_command: target/appassembler/bin/IndexReaderUtils
search_command: target/appassembler/bin/SearchCollection
topic_root: src/main/resources/topics-and-qrels/
qrels_root: src/main/resources/topics-and-qrels/
ranking_root:
generator: WashingtonPostGenerator
threads: 1
index_options:
  - -storePositions
  - -storeDocvectors
  - -storeRaw
topic_reader: BackgroundLinking
input_roots:
  - /tuna1/      # on tuna
  - /store/      # on orca
  - /scratch2/   # on damiano
input: collections/newswire/WashingtonPost.v3/data/
index_path: indexes/lucene-index.core18-v3.pos+docvectors+raw
collection: WashingtonPostCollection
index_stats:
  documents: 671945
  documents (non-empty): 671945
  total terms: 366108299
topics:
  - name: "[TREC 2020 Topics](../src/main/resources/topics-and-qrels/topics.backgroundlinking20.txt)"
    path: topics.backgroundlinking20.txt
    qrel: qrels.backgroundlinking20.txt
evals:
  - command: tools/eval/trec_eval.9.0.4/trec_eval
    params:
      - -c -M1000 -m ndcg_cut.5
    separator: "\t"
    parse_index: 2
    metric: NCDG@5
    metric_precision: 4
    can_combine: true
  - command: tools/eval/trec_eval.9.0.4/trec_eval
    params:
      - -c -M1000 -m map
    separator: "\t"
    parse_index: 2
    metric: AP
    metric_precision: 4
    can_combine: true
models:
  - name: bm25
    display: BM25
    params:
      - -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100
    results:
      AP:
        - 0.3286
      NCDG@5:
        - 0.5231
  - name: bm25+rm3
    display: +RM3
    params:
      - -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100
    results:
      AP:
        - 0.4504
      NCDG@5:
        - 0.5673
  - name: bm25+rm3+df
    display: +RM3+DF
    params:
      - -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100
    results:
      AP:
        - 0.3421
      NCDG@5:
        - 0.5279