Joint relational embeddings for knowledge-based question answering

Min Chul Yang, Nan Duan, Ming Zhou, Hae-Chang Rim

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

35 Citations (Scopus)

Abstract

Transforming a natural language (NL) question into a corresponding logical form (LF) is central to the knowledge-based question answering (KB-QA) task. Unlike most previous methods that achieve this goal based on mappings between lexicalized phrases and logical predicates, this paper goes one step further and proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space. Experimental results demonstrate that our proposed method outperforms three KB-QA baseline methods on two publicly released QA data sets.

Original languageEnglish
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages645-650
Number of pages6
ISBN (Electronic)9781937284961
Publication statusPublished - 2014
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: 2014 Oct 252014 Oct 29

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period14/10/2514/10/29

Fingerprint

Semantics

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Yang, M. C., Duan, N., Zhou, M., & Rim, H-C. (2014). Joint relational embeddings for knowledge-based question answering. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 645-650). Association for Computational Linguistics (ACL).

Joint relational embeddings for knowledge-based question answering. / Yang, Min Chul; Duan, Nan; Zhou, Ming; Rim, Hae-Chang.

EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 645-650.

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

Yang, MC, Duan, N, Zhou, M & Rim, H-C 2014, Joint relational embeddings for knowledge-based question answering. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 645-650, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 14/10/25.
Yang MC, Duan N, Zhou M, Rim H-C. Joint relational embeddings for knowledge-based question answering. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 645-650
Yang, Min Chul ; Duan, Nan ; Zhou, Ming ; Rim, Hae-Chang. / Joint relational embeddings for knowledge-based question answering. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 645-650
@inproceedings{0cc45565e1f44c12a4e3583a67e1583a,
title = "Joint relational embeddings for knowledge-based question answering",
abstract = "Transforming a natural language (NL) question into a corresponding logical form (LF) is central to the knowledge-based question answering (KB-QA) task. Unlike most previous methods that achieve this goal based on mappings between lexicalized phrases and logical predicates, this paper goes one step further and proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space. Experimental results demonstrate that our proposed method outperforms three KB-QA baseline methods on two publicly released QA data sets.",
author = "Yang, {Min Chul} and Nan Duan and Ming Zhou and Hae-Chang Rim",
year = "2014",
language = "English",
pages = "645--650",
booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Joint relational embeddings for knowledge-based question answering

AU - Yang, Min Chul

AU - Duan, Nan

AU - Zhou, Ming

AU - Rim, Hae-Chang

PY - 2014

Y1 - 2014

N2 - Transforming a natural language (NL) question into a corresponding logical form (LF) is central to the knowledge-based question answering (KB-QA) task. Unlike most previous methods that achieve this goal based on mappings between lexicalized phrases and logical predicates, this paper goes one step further and proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space. Experimental results demonstrate that our proposed method outperforms three KB-QA baseline methods on two publicly released QA data sets.

AB - Transforming a natural language (NL) question into a corresponding logical form (LF) is central to the knowledge-based question answering (KB-QA) task. Unlike most previous methods that achieve this goal based on mappings between lexicalized phrases and logical predicates, this paper goes one step further and proposes a novel embedding-based approach that maps NL-questions into LFs for KBQA by leveraging semantic associations between lexical representations and KBproperties in the latent space. Experimental results demonstrate that our proposed method outperforms three KB-QA baseline methods on two publicly released QA data sets.

UR - http://www.scopus.com/inward/record.url?scp=84926018829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926018829&partnerID=8YFLogxK

M3 - Conference contribution

SP - 645

EP - 650

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -