Learning structured natural language representations for semantic parsing

Jianpeng Cheng; Siva Reddy; Vijay Saraswat; Mirella Lapata

doi:10.18653/v1/P17-1005

Learning structured natural language representations for semantic parsing

Jianpeng Cheng, Siva Reddy, Vijay Saraswat, Mirella Lapata

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

Abstract

We introduce a neural semantic parser which is interpretable and scalable. Our model converts natural language utterances to intermediate, domain-general natural language representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We achieve the state of the art on SPADES and GRAPHQUESTIONS and obtain competitive results on GEO-QUERY and WEBQUESTIONS. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.

Original language	English
Title of host publication	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	44-55
Number of pages	12
Volume	1
ISBN (Electronic)	9781945626753
DOIs	https://doi.org/10.18653/v1/P17-1005
Publication status	E-pub ahead of print - 4 Aug 2017
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17

Access to Document

10.18653/v1/P17-1005

P17-1005Final published version, 217 KB

Cite this

Cheng, J., Reddy, S., Saraswat, V., & Lapata, M. (2017). Learning structured natural language representations for semantic parsing. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 44-55). Association for Computational Linguistics (ACL). Advance online publication. https://doi.org/10.18653/v1/P17-1005

@inproceedings{7b8e87a3030145aba495f5f35f0fe408,

title = "Learning structured natural language representations for semantic parsing",

abstract = "We introduce a neural semantic parser which is interpretable and scalable. Our model converts natural language utterances to intermediate, domain-general natural language representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We achieve the state of the art on SPADES and GRAPHQUESTIONS and obtain competitive results on GEO-QUERY and WEBQUESTIONS. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.",

author = "Jianpeng Cheng and Siva Reddy and Vijay Saraswat and Mirella Lapata",

year = "2017",

month = aug,

day = "4",

doi = "10.18653/v1/P17-1005",

language = "English",

volume = "1",

pages = "44--55",

booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

publisher = "Association for Computational Linguistics (ACL)",

note = "55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

}

Cheng, J, Reddy, S, Saraswat, V & Lapata, M 2017, Learning structured natural language representations for semantic parsing. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). vol. 1, Association for Computational Linguistics (ACL), pp. 44-55, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1005

Learning structured natural language representations for semantic parsing. / Cheng, Jianpeng; Reddy, Siva; Saraswat, Vijay et al.
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 Association for Computational Linguistics (ACL), 2017. p. 44-55.

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

TY - GEN

T1 - Learning structured natural language representations for semantic parsing

AU - Cheng, Jianpeng

AU - Reddy, Siva

AU - Saraswat, Vijay

AU - Lapata, Mirella

PY - 2017/8/4

Y1 - 2017/8/4

N2 - We introduce a neural semantic parser which is interpretable and scalable. Our model converts natural language utterances to intermediate, domain-general natural language representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We achieve the state of the art on SPADES and GRAPHQUESTIONS and obtain competitive results on GEO-QUERY and WEBQUESTIONS. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.

AB - We introduce a neural semantic parser which is interpretable and scalable. Our model converts natural language utterances to intermediate, domain-general natural language representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We achieve the state of the art on SPADES and GRAPHQUESTIONS and obtain competitive results on GEO-QUERY and WEBQUESTIONS. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.

UR - http://www.scopus.com/inward/record.url?scp=85040945898&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-1005

DO - 10.18653/v1/P17-1005

M3 - Conference contribution

AN - SCOPUS:85040945898

VL - 1

SP - 44

EP - 55

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - Association for Computational Linguistics (ACL)

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Learning structured natural language representations for semantic parsing

Abstract

Conference

Access to Document

Other files and links

Fingerprint

TransModal: Translating from Multiple Modalities into Text

Cite this

Learning structured natural language representations for semantic parsing

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

TransModal: Translating from Multiple Modalities into Text

Cite this