Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains

In this paper, we study how to improve thedomain adaptability of a deletion-basedLong Short-Term Memory (LSTM) neuralnetwork model for sentence compression.We hypothesize that syntactic informationhelps in making such modelsmore robust across domains. We proposetwo major changes to the model: usinge...

Full description

Saved in:

Bibliographic Details
Main Authors:	WANG, Liangguo, JIANG, Jing, CHIEU, Hai Leong, ONG, Chen Hui, SONG, Dandan, LIAO, Lejian
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2017
Subjects:	Databases and Information Systems Programming Languages and Compilers
Online Access:	https://ink.library.smu.edu.sg/sis_research/3901 https://ink.library.smu.edu.sg/context/sis_research/article/4903/viewcontent/P17_1127.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-4903
record_format	dspace
spelling	sg-smu-ink.sis_research-49032018-01-11T06:54:55Z Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains WANG, Liangguo JIANG, Jing CHIEU, Hai Leong ONG, Chen Hui SONG, Dandan LIAO, Lejian In this paper, we study how to improve thedomain adaptability of a deletion-basedLong Short-Term Memory (LSTM) neuralnetwork model for sentence compression.We hypothesize that syntactic informationhelps in making such modelsmore robust across domains. We proposetwo major changes to the model: usingexplicit syntactic features and introducingsyntactic constraints through Integer LinearProgramming (ILP). Our evaluationshows that the proposed model works betterthan the original model as well as a traditionalnon-neural-network-based modelin a cross-domain setting. 2017-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3901 info:doi/10.18653/v1/P17-1127 https://ink.library.smu.edu.sg/context/sis_research/article/4903/viewcontent/P17_1127.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Programming Languages and Compilers
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Databases and Information Systems Programming Languages and Compilers
spellingShingle	Databases and Information Systems Programming Languages and Compilers WANG, Liangguo JIANG, Jing CHIEU, Hai Leong ONG, Chen Hui SONG, Dandan LIAO, Lejian Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
description	In this paper, we study how to improve thedomain adaptability of a deletion-basedLong Short-Term Memory (LSTM) neuralnetwork model for sentence compression.We hypothesize that syntactic informationhelps in making such modelsmore robust across domains. We proposetwo major changes to the model: usingexplicit syntactic features and introducingsyntactic constraints through Integer LinearProgramming (ILP). Our evaluationshows that the proposed model works betterthan the original model as well as a traditionalnon-neural-network-based modelin a cross-domain setting.
format	text
author	WANG, Liangguo JIANG, Jing CHIEU, Hai Leong ONG, Chen Hui SONG, Dandan LIAO, Lejian
author_facet	WANG, Liangguo JIANG, Jing CHIEU, Hai Leong ONG, Chen Hui SONG, Dandan LIAO, Lejian
author_sort	WANG, Liangguo
title	Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
title_short	Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
title_full	Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
title_fullStr	Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
title_full_unstemmed	Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
title_sort	can syntax help? improving an lstm-based sentence compression model for new domains
publisher	Institutional Knowledge at Singapore Management University
publishDate	2017
url	https://ink.library.smu.edu.sg/sis_research/3901 https://ink.library.smu.edu.sg/context/sis_research/article/4903/viewcontent/P17_1127.pdf
_version_	1770573899961991168

Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains

Similar Items