A System for Automatic English Text Expansion

Silvia García-Méndez; Milagros Fernández-Gavilanes; Enrique Costa-Montenegro; Jonathan Juncal-Martínez; Francisco J. González-Castaño; Ehud Reiter

doi:10.1109/ACCESS.2019.2937505

A System for Automatic English Text Expansion

Silvia García-Méndez (Corresponding Author), Milagros Fernández-Gavilanes, Enrique Costa-Montenegro, Jonathan Juncal-Martínez, Francisco J. González-Castaño, Ehud Reiter

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

5 Downloads (Pure)

Abstract

We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, “automatic” means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adaptable to other languages. This adaptability is one of its greatest advantages. For English, we have created the highly precise aLexiE lexicon with wide coverage, which represents a contribution on its own. We have evaluated the resulting NLG library in an Augmentative and Alternative Communication (AAC) proof of concept, both directly (by regenerating corpus sentences) and manually (from annotations) using a popular corpus in the NLG field. We performed a second analysis by comparing the quality of text expansion in English to Spanish, using an ad-hoc Spanish-English parallel corpus. The system might also be applied to other domains such as report and news generation.

Original language	English
Pages (from-to)	123320-123333
Number of pages	14
Journal	IEEE Access
Volume	7
Issue number	1
Early online date	26 Aug 2019
DOIs	https://doi.org/10.1109/ACCESS.2019.2937505
Publication status	Published - Dec 2019

Bibliographical note

This work was supported in part by the Mineco, Spain, under Grant TEC2016-76465-C2-2-R, in part by the Xunta de Galicia, Spain, under Grant GRC-2018/53 and Grant ED341D R2016/012, and in part by the University of Vigo Travel Grant to visit the CLAN Research Group, University of Aberdeen, U.K.

Keywords

Grammar
Linguistics
Transforms
Licenses
Heuristic algorithms
Syntactics
Augmentative and Alternative Communication
Natural Language Generation
sentence planning
surface realiser
text expansion

Access to Document

10.1109/ACCESS.2019.2937505Licence: CC BY

A System for Automatic English Text Expansion
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/
Final published version, 8.21 MBLicence: CC BY

Cite this

@article{4fda824aa25c4344bb190b1fcafd517e,

title = "A System for Automatic English Text Expansion",

abstract = "We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, “automatic” means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adaptable to other languages. This adaptability is one of its greatest advantages. For English, we have created the highly precise aLexiE lexicon with wide coverage, which represents a contribution on its own. We have evaluated the resulting NLG library in an Augmentative and Alternative Communication (AAC) proof of concept, both directly (by regenerating corpus sentences) and manually (from annotations) using a popular corpus in the NLG field. We performed a second analysis by comparing the quality of text expansion in English to Spanish, using an ad-hoc Spanish-English parallel corpus. The system might also be applied to other domains such as report and news generation.",

keywords = "Grammar, Linguistics, Transforms, Licenses, Heuristic algorithms, Syntactics, Augmentative and Alternative Communication, Natural Language Generation, sentence planning, surface realiser, text expansion",

author = "Silvia Garc{\'i}a-M{\'e}ndez and Milagros Fern{\'a}ndez-Gavilanes and Enrique Costa-Montenegro and Jonathan Juncal-Mart{\'i}nez and Gonz{\'a}lez-Casta{\~n}o, {Francisco J.} and Ehud Reiter",

note = "This work was supported in part by the Mineco, Spain, under Grant TEC2016-76465-C2-2-R, in part by the Xunta de Galicia, Spain, under Grant GRC-2018/53 and Grant ED341D R2016/012, and in part by the University of Vigo Travel Grant to visit the CLAN Research Group, University of Aberdeen, U.K.",

year = "2019",

month = dec,

doi = "10.1109/ACCESS.2019.2937505",

language = "English",

volume = "7",

pages = "123320--123333",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "IEEE Explore",

number = "1",

}

TY - JOUR

T1 - A System for Automatic English Text Expansion

AU - García-Méndez, Silvia

AU - Fernández-Gavilanes, Milagros

AU - Costa-Montenegro, Enrique

AU - Juncal-Martínez, Jonathan

AU - González-Castaño, Francisco J.

AU - Reiter, Ehud

N1 - This work was supported in part by the Mineco, Spain, under Grant TEC2016-76465-C2-2-R, in part by the Xunta de Galicia, Spain, under Grant GRC-2018/53 and Grant ED341D R2016/012, and in part by the University of Vigo Travel Grant to visit the CLAN Research Group, University of Aberdeen, U.K.

PY - 2019/12

Y1 - 2019/12

N2 - We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, “automatic” means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adaptable to other languages. This adaptability is one of its greatest advantages. For English, we have created the highly precise aLexiE lexicon with wide coverage, which represents a contribution on its own. We have evaluated the resulting NLG library in an Augmentative and Alternative Communication (AAC) proof of concept, both directly (by regenerating corpus sentences) and manually (from annotations) using a popular corpus in the NLG field. We performed a second analysis by comparing the quality of text expansion in English to Spanish, using an ad-hoc Spanish-English parallel corpus. The system might also be applied to other domains such as report and news generation.

AB - We present an automatic text expansion system to generate English sentences, which performs automatic Natural Language Generation (NLG) by combining linguistic rules with statistical approaches. Here, “automatic” means that the system can generate coherent and correct sentences from a minimum set of words. From its inception, the design is modular and adaptable to other languages. This adaptability is one of its greatest advantages. For English, we have created the highly precise aLexiE lexicon with wide coverage, which represents a contribution on its own. We have evaluated the resulting NLG library in an Augmentative and Alternative Communication (AAC) proof of concept, both directly (by regenerating corpus sentences) and manually (from annotations) using a popular corpus in the NLG field. We performed a second analysis by comparing the quality of text expansion in English to Spanish, using an ad-hoc Spanish-English parallel corpus. The system might also be applied to other domains such as report and news generation.

KW - Grammar

KW - Linguistics

KW - Transforms

KW - Licenses

KW - Heuristic algorithms

KW - Syntactics

KW - Augmentative and Alternative Communication

KW - Natural Language Generation

KW - sentence planning

KW - surface realiser

KW - text expansion

UR - http://www.mendeley.com/research/system-automatic-english-text-expansion

U2 - 10.1109/ACCESS.2019.2937505

DO - 10.1109/ACCESS.2019.2937505

M3 - Article

SN - 2169-3536

VL - 7

SP - 123320

EP - 123333

JO - IEEE Access

JF - IEEE Access

IS - 1

ER -

A System for Automatic English Text Expansion

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Ehud Reiter

Cite this

A System for Automatic English Text Expansion

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Profiles

Ehud Reiter

Cite this