Translation of natural language query into keyword query using a rnn encoder-decoder

Hyun Je Song; A. Yeong Kim; Seong Bae Park

doi:10.1145/3077136.3080691

Translation of natural language query into keyword query using a rnn encoder-decoder

Hyun Je Song
, A. Yeong Kim
, Seong Bae Park

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Citations (Scopus)

Abstract

The number of natural language queries submi.ed to search engines is increasing as search environments get diversified. However, legacy search engines are still optimized for short keyword queries.Thus, the use of natural language queries at legacy search engines degrades the retrieval performance of the engines. This paper proposes a novel method to translate a natural language query into a keyword query relevant to the natural language query for retrieving beffer search results without change of the engines. .The proposed method formulates the translation as a generation task. .that is, the method generates a keyword query from a natural language query by preserving the semantics of the natural language query. A recurrent neural network encoder-decoder architecture is adopted as a generator of keyword queries from natural language queries. In addition, an a.ention mechanism is also used to cope with long natural language queries.

Original language	English
Title of host publication	SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher	Association for Computing Machinery, Inc
Pages	965-968
Number of pages	4
ISBN (Electronic)	9781450350228
DOIs	https://doi.org/10.1145/3077136.3080691
Publication status	Published - 7 Aug 2017
Event	40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2017 - Tokyo, Shinjuku, Japan Duration: 7 Aug 2017 → 11 Aug 2017

Publication series

Name	SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference	40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2017
Country/Territory	Japan
City	Tokyo, Shinjuku
Period	7/08/17 → 11/08/17

Bibliographical note

Publisher Copyright:
© 2017 Copyright held by the owner/author(s).

Keywords

Neural machine translation
Query reformulation
RNN encoder-decoder
Translation natural language query into keyword query

Access to Document

10.1145/3077136.3080691

Cite this

Song, H. J., Kim, A. Y., & Park, S. B. (2017). Translation of natural language query into keyword query using a rnn encoder-decoder. In SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 965-968). (SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval). Association for Computing Machinery, Inc. https://doi.org/10.1145/3077136.3080691

Song, Hyun Je ; Kim, A. Yeong ; Park, Seong Bae. / Translation of natural language query into keyword query using a rnn encoder-decoder. SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2017. pp. 965-968 (SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval).

@inproceedings{7db32d63643a44abb85d414b8e8d70ae,

title = "Translation of natural language query into keyword query using a rnn encoder-decoder",

abstract = "The number of natural language queries submi.ed to search engines is increasing as search environments get diversified. However, legacy search engines are still optimized for short keyword queries.Thus, the use of natural language queries at legacy search engines degrades the retrieval performance of the engines. This paper proposes a novel method to translate a natural language query into a keyword query relevant to the natural language query for retrieving beffer search results without change of the engines. .The proposed method formulates the translation as a generation task. .that is, the method generates a keyword query from a natural language query by preserving the semantics of the natural language query. A recurrent neural network encoder-decoder architecture is adopted as a generator of keyword queries from natural language queries. In addition, an a.ention mechanism is also used to cope with long natural language queries.",

keywords = "Neural machine translation, Query reformulation, RNN encoder-decoder, Translation natural language query into keyword query",

author = "Song, \{Hyun Je\} and Kim, \{A. Yeong\} and Park, \{Seong Bae\}",

note = "Publisher Copyright: {\textcopyright} 2017 Copyright held by the owner/author(s).; 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2017 ; Conference date: 07-08-2017 Through 11-08-2017",

year = "2017",

month = aug,

day = "7",

doi = "10.1145/3077136.3080691",

language = "English",

series = "SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval",

publisher = "Association for Computing Machinery, Inc",

pages = "965--968",

booktitle = "SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval",

}

Song, HJ, Kim, AY & Park, SB 2017, Translation of natural language query into keyword query using a rnn encoder-decoder. in SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, Inc, pp. 965-968, 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2017, Tokyo, Shinjuku, Japan, 7/08/17. https://doi.org/10.1145/3077136.3080691

Translation of natural language query into keyword query using a rnn encoder-decoder. / Song, Hyun Je; Kim, A. Yeong; Park, Seong Bae.
SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2017. p. 965-968 (SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Translation of natural language query into keyword query using a rnn encoder-decoder

AU - Song, Hyun Je

AU - Kim, A. Yeong

AU - Park, Seong Bae

PY - 2017/8/7

Y1 - 2017/8/7

N2 - The number of natural language queries submi.ed to search engines is increasing as search environments get diversified. However, legacy search engines are still optimized for short keyword queries.Thus, the use of natural language queries at legacy search engines degrades the retrieval performance of the engines. This paper proposes a novel method to translate a natural language query into a keyword query relevant to the natural language query for retrieving beffer search results without change of the engines. .The proposed method formulates the translation as a generation task. .that is, the method generates a keyword query from a natural language query by preserving the semantics of the natural language query. A recurrent neural network encoder-decoder architecture is adopted as a generator of keyword queries from natural language queries. In addition, an a.ention mechanism is also used to cope with long natural language queries.

AB - The number of natural language queries submi.ed to search engines is increasing as search environments get diversified. However, legacy search engines are still optimized for short keyword queries.Thus, the use of natural language queries at legacy search engines degrades the retrieval performance of the engines. This paper proposes a novel method to translate a natural language query into a keyword query relevant to the natural language query for retrieving beffer search results without change of the engines. .The proposed method formulates the translation as a generation task. .that is, the method generates a keyword query from a natural language query by preserving the semantics of the natural language query. A recurrent neural network encoder-decoder architecture is adopted as a generator of keyword queries from natural language queries. In addition, an a.ention mechanism is also used to cope with long natural language queries.

KW - Neural machine translation

KW - Query reformulation

KW - RNN encoder-decoder

KW - Translation natural language query into keyword query

UR - https://www.scopus.com/pages/publications/85029354159

U2 - 10.1145/3077136.3080691

DO - 10.1145/3077136.3080691

M3 - Conference contribution

AN - SCOPUS:85029354159

T3 - SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

SP - 965

EP - 968

BT - SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery, Inc

T2 - 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2017

Y2 - 7 August 2017 through 11 August 2017

ER -

Song HJ, Kim AY, Park SB. Translation of natural language query into keyword query using a rnn encoder-decoder. In SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc. 2017. p. 965-968. (SIGIR 2017 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval). doi: 10.1145/3077136.3080691

Translation of natural language query into keyword query using a rnn encoder-decoder

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this