Task-oriented query reformulation with reinforcement learning

Rodrigo Nogueira, Kyunghyun Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned. We train this neural network with reinforcement learning. The actions correspond to selecting terms to build a reformulated query, and the reward is the document recall. We evaluate our approach on three datasets against strong baselines and show a relative improvement of 5-20% in terms of recall. Furthermore, we present a simple method to estimate a conservative upper-bound performance of a model in a particular environment and verify that there is still large room for improvements.

Original languageEnglish (US)
Title of host publicationEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages574-583
Number of pages10
ISBN (Electronic)9781945626838
StatePublished - Jan 1 2017
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: Sep 9 2017Sep 11 2017

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
CountryDenmark
CityCopenhagen
Period9/9/179/11/17

Fingerprint

Reinforcement learning
Neural networks
Search engines

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Cite this

Nogueira, R., & Cho, K. (2017). Task-oriented query reformulation with reinforcement learning. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 574-583). (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL).

Task-oriented query reformulation with reinforcement learning. / Nogueira, Rodrigo; Cho, Kyunghyun.

EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. p. 574-583 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nogueira, R & Cho, K 2017, Task-oriented query reformulation with reinforcement learning. in EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), pp. 574-583, 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9/9/17.
Nogueira R, Cho K. Task-oriented query reformulation with reinforcement learning. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL). 2017. p. 574-583. (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
Nogueira, Rodrigo ; Cho, Kyunghyun. / Task-oriented query reformulation with reinforcement learning. EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2017. pp. 574-583 (EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
@inproceedings{567c83cffb774bd7be77a2670b5de531,
title = "Task-oriented query reformulation with reinforcement learning",
abstract = "Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned. We train this neural network with reinforcement learning. The actions correspond to selecting terms to build a reformulated query, and the reward is the document recall. We evaluate our approach on three datasets against strong baselines and show a relative improvement of 5-20{\%} in terms of recall. Furthermore, we present a simple method to estimate a conservative upper-bound performance of a model in a particular environment and verify that there is still large room for improvements.",
author = "Rodrigo Nogueira and Kyunghyun Cho",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
series = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "574--583",
booktitle = "EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

}

TY - GEN

T1 - Task-oriented query reformulation with reinforcement learning

AU - Nogueira, Rodrigo

AU - Cho, Kyunghyun

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned. We train this neural network with reinforcement learning. The actions correspond to selecting terms to build a reformulated query, and the reward is the document recall. We evaluate our approach on three datasets against strong baselines and show a relative improvement of 5-20% in terms of recall. Furthermore, we present a simple method to estimate a conservative upper-bound performance of a model in a particular environment and verify that there is still large room for improvements.

AB - Search engines play an important role in our everyday lives by assisting us in finding the information we need. When we input a complex query, however, results are often far from satisfactory. In this work, we introduce a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned. We train this neural network with reinforcement learning. The actions correspond to selecting terms to build a reformulated query, and the reward is the document recall. We evaluate our approach on three datasets against strong baselines and show a relative improvement of 5-20% in terms of recall. Furthermore, we present a simple method to estimate a conservative upper-bound performance of a model in a particular environment and verify that there is still large room for improvements.

UR - http://www.scopus.com/inward/record.url?scp=85073162792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073162792&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85073162792

T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 574

EP - 583

BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -