Incremental Grammar Induction from Child-directed Dialogue Utterances

Arash Eshghi; Julian Hough; Matthew Purver

Incremental Grammar Induction from Child-directed Dialogue Utterances

Arash Eshghi, Julian Hough, Matthew Purver

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

Abstract

We describe a method for learning an incremental semantic grammar from data in which utterances are paired with logical forms representing their meaning. Working in an inherently incremental framework, Dynamic Syntax, we show how words can be associated with probabilistic procedures for the incremental projection of meaning, providing a grammar which can be used directly in incremental probabilistic parsing and generation. We test this on child-directed utterances from the CHILDES corpus, and show that it results in good coverage and semantic accuracy, without requiring annotation at the word level or any independent notion of syntax.

Original language	English
Title of host publication	Proceedings of the Fourth Annual Workshop on Cognitive Modeling and Computational Linguistics
Publisher	Association for Computational Linguistics
Pages	94-103
Number of pages	10
Publication status	Published - 2013
Event	51st Annual Meeting of the Association for Computational Linguistics - Sofia, Bulgaria Duration: 4 Aug 2013 → 9 Aug 2013 http://www.acl2013.org/site/

Conference

Conference	51st Annual Meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2013
Country/Territory	Bulgaria
City	Sofia
Period	4/08/13 → 9/08/13
Internet address	http://www.acl2013.org/site/

Access to Document

https://aclanthology.info/papers/W13-2611/w13-2611

Cite this

@inproceedings{c0e5df414d0546f39e7ab428dd73d6a6,

title = "Incremental Grammar Induction from Child-directed Dialogue Utterances",

abstract = "We describe a method for learning an incremental semantic grammar from data in which utterances are paired with logical forms representing their meaning. Working in an inherently incremental framework, Dynamic Syntax, we show how words can be associated with probabilistic procedures for the incremental projection of meaning, providing a grammar which can be used directly in incremental probabilistic parsing and generation. We test this on child-directed utterances from the CHILDES corpus, and show that it results in good coverage and semantic accuracy, without requiring annotation at the word level or any independent notion of syntax.",

author = "Arash Eshghi and Julian Hough and Matthew Purver",

year = "2013",

language = "English",

pages = "94--103",

booktitle = "Proceedings of the Fourth Annual Workshop on Cognitive Modeling and Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 ; Conference date: 04-08-2013 Through 09-08-2013",

url = "http://www.acl2013.org/site/",

}

Eshghi, A, Hough, J & Purver, M 2013, Incremental Grammar Induction from Child-directed Dialogue Utterances. in Proceedings of the Fourth Annual Workshop on Cognitive Modeling and Computational Linguistics. Association for Computational Linguistics, pp. 94-103, 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, 4/08/13. <https://aclanthology.info/papers/W13-2611/w13-2611>

TY - GEN

T1 - Incremental Grammar Induction from Child-directed Dialogue Utterances

AU - Eshghi, Arash

AU - Hough, Julian

AU - Purver, Matthew

PY - 2013

Y1 - 2013

N2 - We describe a method for learning an incremental semantic grammar from data in which utterances are paired with logical forms representing their meaning. Working in an inherently incremental framework, Dynamic Syntax, we show how words can be associated with probabilistic procedures for the incremental projection of meaning, providing a grammar which can be used directly in incremental probabilistic parsing and generation. We test this on child-directed utterances from the CHILDES corpus, and show that it results in good coverage and semantic accuracy, without requiring annotation at the word level or any independent notion of syntax.

AB - We describe a method for learning an incremental semantic grammar from data in which utterances are paired with logical forms representing their meaning. Working in an inherently incremental framework, Dynamic Syntax, we show how words can be associated with probabilistic procedures for the incremental projection of meaning, providing a grammar which can be used directly in incremental probabilistic parsing and generation. We test this on child-directed utterances from the CHILDES corpus, and show that it results in good coverage and semantic accuracy, without requiring annotation at the word level or any independent notion of syntax.

M3 - Conference contribution

SP - 94

EP - 103

BT - Proceedings of the Fourth Annual Workshop on Cognitive Modeling and Computational Linguistics

PB - Association for Computational Linguistics

T2 - 51st Annual Meeting of the Association for Computational Linguistics

Y2 - 4 August 2013 through 9 August 2013

ER -

Incremental Grammar Induction from Child-directed Dialogue Utterances

Abstract

Conference

Access to Document

Fingerprint

Cite this