Unsupervised Sentence Simplification Using Deep Semantics

Shashi Narayan; Claire Gardent

doi:10.18653/v1/W16-6620

Unsupervised Sentence Simplification Using Deep Semantics

Shashi Narayan, Claire Gardent

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

Abstract

We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.

Original language	English
Title of host publication	Proceedings of The 9th International Natural Language Generation conference
Place of Publication	Edinburgh. UK
Publisher	Association for Computational Linguistics
Pages	111-120
Number of pages	10
DOIs	https://doi.org/10.18653/v1/W16-6620
Publication status	Published - 8 Sept 2016
Event	9th International Natural Language Generation conference - Edinburgh, United Kingdom Duration: 5 Sept 2016 → 8 Sept 2016 http://www.macs.hw.ac.uk/InteractionLab/INLG2016/

Conference

Conference	9th International Natural Language Generation conference
Abbreviated title	INLG 2016
Country/Territory	United Kingdom
City	Edinburgh
Period	5/09/16 → 8/09/16
Internet address	http://www.macs.hw.ac.uk/InteractionLab/INLG2016/

Access to Document

10.18653/v1/W16-6620

inlg_2016_simplificationAccepted author manuscript, 112 KB

SUMMA - Scalable Understanding of Mulitingual Media
Renals, S., Birch-Mayne, A. & Cohen, S.
EU government bodies
1/02/16 → 31/01/19
Project: Research
Large Scale Unsupervised Parsing for Resource-Poor Languages
Cohen, S.
EPSRC
11/11/14 → 10/02/16
Project: Research

Cite this

@inproceedings{5af7a591fd9f43fe89d7a88e79ff19ca,

title = "Unsupervised Sentence Simplification Using Deep Semantics",

abstract = "We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.",

author = "Shashi Narayan and Claire Gardent",

year = "2016",

month = sep,

day = "8",

doi = "10.18653/v1/W16-6620",

language = "English",

pages = "111--120",

booktitle = "Proceedings of The 9th International Natural Language Generation conference",

publisher = "Association for Computational Linguistics",

note = "9th International Natural Language Generation conference , INLG 2016 ; Conference date: 05-09-2016 Through 08-09-2016",

url = "http://www.macs.hw.ac.uk/InteractionLab/INLG2016/",

}

Narayan, S & Gardent, C 2016, Unsupervised Sentence Simplification Using Deep Semantics. in Proceedings of The 9th International Natural Language Generation conference. Association for Computational Linguistics, Edinburgh. UK, pp. 111-120, 9th International Natural Language Generation conference , Edinburgh, United Kingdom, 5/09/16. https://doi.org/10.18653/v1/W16-6620

TY - GEN

T1 - Unsupervised Sentence Simplification Using Deep Semantics

AU - Narayan, Shashi

AU - Gardent, Claire

PY - 2016/9/8

Y1 - 2016/9/8

N2 - We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.

AB - We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.

U2 - 10.18653/v1/W16-6620

DO - 10.18653/v1/W16-6620

M3 - Conference contribution

SP - 111

EP - 120

BT - Proceedings of The 9th International Natural Language Generation conference

PB - Association for Computational Linguistics

CY - Edinburgh. UK

T2 - 9th International Natural Language Generation conference

Y2 - 5 September 2016 through 8 September 2016

ER -

Unsupervised Sentence Simplification Using Deep Semantics

Abstract

Conference

Access to Document

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Large Scale Unsupervised Parsing for Resource-Poor Languages

Cite this