Skip to content

Latest commit

 

History

History
93 lines (63 loc) · 6.18 KB

regressions-core18.md

File metadata and controls

93 lines (63 loc) · 6.18 KB
Raw

Anserini: Regressions for the Washington Post (Core18)

This page describes regressions for the TREC 2018 Common Core Track, which uses the TREC Washington Post Corpus. The exact configurations for these regressions are stored in this YAML file. Note that this page is automatically generated from this template as part of Anserini's regression pipeline, so do not modify this page directly; modify the template instead.

Indexing

Typical indexing command:

nohup sh target/appassembler/bin/IndexCollection -collection WashingtonPostCollection -input /path/to/core18 \
 -index indexes/lucene-index.core18.pos+docvectors+raw -generator WashingtonPostGenerator -threads 1 \
 -storePositions -storeDocvectors -storeRaw >& logs/log.core18.pos+docvectors+rawdocs &

The directory /path/to/core18/ should be the root directory of the TREC Washington Post Corpus, i.e., ls /path/to/core18/ should bring up a single JSON file.

For additional details, see explanation of common indexing options.

Retrieval

Topics and qrels are stored in src/main/resources/topics-and-qrels/, downloaded from NIST:

After indexing has completed, you should be able to perform retrieval as follows:

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -bm25 -output run.core18.bm25.topics.core18.txt &

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -bm25 -rm3 -output run.core18.bm25+rm3.topics.core18.txt &

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -bm25 -axiom -axiom.deterministic -rerankCutoff 20 -output run.core18.bm25+ax.topics.core18.txt &

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -qld -output run.core18.ql.topics.core18.txt &

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -qld -rm3 -output run.core18.ql+rm3.topics.core18.txt &

nohup target/appassembler/bin/SearchCollection -index indexes/lucene-index.core18.pos+docvectors+raw \
 -topicreader Trec -topics src/main/resources/topics-and-qrels/topics.core18.txt \
 -qld -axiom -axiom.deterministic -rerankCutoff 20 -output run.core18.ql+ax.topics.core18.txt &

Evaluation can be performed using trec_eval:

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.bm25.topics.core18.txt

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.bm25+rm3.topics.core18.txt

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.bm25+ax.topics.core18.txt

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.ql.topics.core18.txt

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.ql+rm3.topics.core18.txt

eval/trec_eval.9.0.4/trec_eval -m map -m P.30 src/main/resources/topics-and-qrels/qrels.core18.txt run.core18.ql+ax.topics.core18.txt

Effectiveness

With the above commands, you should be able to replicate the following results:

MAP BM25 +RM3 +Ax QL +RM3 +Ax
TREC 2018 Common Core Track Topics 0.2495 0.3135 0.2841 0.2526 0.3073 0.2919
P30 BM25 +RM3 +Ax QL +RM3 +Ax
TREC 2018 Common Core Track Topics 0.3567 0.4200 0.3947 0.3653 0.4000 0.4020

Replication Log