
regression.msmarco-doc-segmented-unicoil.yaml Maven / Gradle / Ivy
---
corpus: msmarco-doc-segmented-unicoil
corpus_path: collections/msmarco/msmarco-doc-segmented-unicoil/
download_url: https://rgw.cs.uwaterloo.ca/JIMMYLIN-bucket0/data/msmarco-doc-segmented-unicoil.tar
download_checksum: 6a00e2c0c375cb1e52c83ae5ac377ebb
index_path: indexes/lucene-index.msmarco-doc-segmented-unicoil/
collection_class: JsonVectorCollection
generator_class: DefaultLuceneDocumentGenerator
index_threads: 16
index_options: -impact -pretokenized -storeDocvectors
index_stats:
documents: 20545677
documents (non-empty): 20545677
total terms: 214505277898
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.unicoil.tsv.gz
qrel: qrels.msmarco-doc.dev.txt
models:
- name: unicoil
display: uniCOIL (with doc2query-T5 expansions)
params: -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
results:
AP@1000:
- 0.3535
RR@100:
- 0.3531
R@100:
- 0.8858
R@1000:
- 0.9546
- name: rm3
display: +RM3
params: -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
results:
AP@1000:
- 0.3186
RR@100:
- 0.3182
R@100:
- 0.8800
R@1000:
- 0.9615
- name: rocchio
display: +Rocchio
params: -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000
results:
AP@1000:
- 0.3256
RR@100:
- 0.3252
R@100:
- 0.8848
R@1000:
- 0.9619
© 2015 - 2025 Weber Informatics LLC | Privacy Policy