Simple readable sub-sentences

Sigrid Klerke; Anders Søgaard

Simple readable sub-sentences

Centre for Language Technology

Abstract

We present experiments using a new unsupervised approach to automatic text simplification, which builds on sampling and ranking via a loss function informed by readability research. The main idea is that a loss function can distinguish good simplification candidates among randomly sampled sub-sentences of the input sentence. Our approach is rated as equally grammatical and beginner reader appropriate as a supervised SMT-based baseline system by native speakers, but our setup performs more radical changes that better resembles the variation observed in human generated simplifications.

Original language	English
Title of host publication	The 51st Annual Meeting of the Association for Computational Linguistics (ACL), Student Research Workshop
Publisher	Association for Computational Linguistics
Publication date	2013
Pages	142-149
ISBN (Electronic)	978-1-62748-976-8
Publication status	Published - 2013

Cite this

@inproceedings{c6a4aa8494f248ec9ec47f6fcb8c4041,

title = "Simple readable sub-sentences",

abstract = "We present experiments using a new unsupervised approach to automatic text simplification, which builds on sampling and ranking via a loss function informed by readability research. The main idea is that a loss function can distinguish good simplification candidates among randomly sampled sub-sentences of the input sentence. Our approach is rated as equally grammatical and beginner reader appropriate as a supervised SMT-based baseline system by native speakers, but our setup performs more radical changes that better resembles the variation observed in human generated simplifications.",

author = "Sigrid Klerke and Anders S{\o}gaard",

year = "2013",

language = "English",

pages = "142--149",

booktitle = "The 51st Annual Meeting of the Association for Computational Linguistics (ACL), Student Research Workshop",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Simple readable sub-sentences

AU - Klerke, Sigrid

AU - Søgaard, Anders

PY - 2013

Y1 - 2013

N2 - We present experiments using a new unsupervised approach to automatic text simplification, which builds on sampling and ranking via a loss function informed by readability research. The main idea is that a loss function can distinguish good simplification candidates among randomly sampled sub-sentences of the input sentence. Our approach is rated as equally grammatical and beginner reader appropriate as a supervised SMT-based baseline system by native speakers, but our setup performs more radical changes that better resembles the variation observed in human generated simplifications.

AB - We present experiments using a new unsupervised approach to automatic text simplification, which builds on sampling and ranking via a loss function informed by readability research. The main idea is that a loss function can distinguish good simplification candidates among randomly sampled sub-sentences of the input sentence. Our approach is rated as equally grammatical and beginner reader appropriate as a supervised SMT-based baseline system by native speakers, but our setup performs more radical changes that better resembles the variation observed in human generated simplifications.

M3 - Article in proceedings

SP - 142

EP - 149

BT - The 51st Annual Meeting of the Association for Computational Linguistics (ACL), Student Research Workshop

PB - Association for Computational Linguistics

ER -

Simple readable sub-sentences

Abstract

Fingerprint

Cite this