BM25 Pseudo Relevance Feedback using Anserini at Waseda university

Zhaohao Zeng, Tetsuya Sakai

研究成果: Conference article

抄録

We built a Docker image for BM25PRF (BM25 with Pseudo Relevance Feedback) retrieval model with Anserini. Also, grid search is provided in the Docker image for parameter tuning. Experimental results suggest that BM25PRF with default parameters outperforms vanilla BM25 on robust04, but tuning parameters on 49 topics of robust04 did not further improve its effectiveness.

元の言語English
ページ(範囲)62-63
ページ数2
ジャーナルCEUR Workshop Proceedings
2409
出版物ステータスPublished - 2019 1 1
イベント2019 Open-Source IR Replicability Challenge, OSIRRC 2019 - Paris, France
継続期間: 2019 7 25 → …

Fingerprint

Tuning
Feedback

ASJC Scopus subject areas

  • Computer Science(all)

これを引用

BM25 Pseudo Relevance Feedback using Anserini at Waseda university. / Zeng, Zhaohao; Sakai, Tetsuya.

:: CEUR Workshop Proceedings, 巻 2409, 01.01.2019, p. 62-63.

研究成果: Conference article

@article{f5b6767ff7504e8699aa63dd10b9bee2,
title = "BM25 Pseudo Relevance Feedback using Anserini at Waseda university",
abstract = "We built a Docker image for BM25PRF (BM25 with Pseudo Relevance Feedback) retrieval model with Anserini. Also, grid search is provided in the Docker image for parameter tuning. Experimental results suggest that BM25PRF with default parameters outperforms vanilla BM25 on robust04, but tuning parameters on 49 topics of robust04 did not further improve its effectiveness.",
author = "Zhaohao Zeng and Tetsuya Sakai",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "2409",
pages = "62--63",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - BM25 Pseudo Relevance Feedback using Anserini at Waseda university

AU - Zeng, Zhaohao

AU - Sakai, Tetsuya

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We built a Docker image for BM25PRF (BM25 with Pseudo Relevance Feedback) retrieval model with Anserini. Also, grid search is provided in the Docker image for parameter tuning. Experimental results suggest that BM25PRF with default parameters outperforms vanilla BM25 on robust04, but tuning parameters on 49 topics of robust04 did not further improve its effectiveness.

AB - We built a Docker image for BM25PRF (BM25 with Pseudo Relevance Feedback) retrieval model with Anserini. Also, grid search is provided in the Docker image for parameter tuning. Experimental results suggest that BM25PRF with default parameters outperforms vanilla BM25 on robust04, but tuning parameters on 49 topics of robust04 did not further improve its effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=85070681063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070681063&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85070681063

VL - 2409

SP - 62

EP - 63

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -