@inproceedings{manishina-etal-2016-automatic,
title = "Automatic Corpus Extension for Data-driven Natural Language Generation",
author = "Manishina, Elena and
Jabaian, Bassam and
Huet, St{\'e}phane and
Lef{\`e}vre, Fabrice",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1575/",
pages = "3624--3631",
abstract = "As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent. Corpus creation and extension in data-driven NLG domain traditionally involved manual paraphrasing performed by either a group of experts or with resort to crowd-sourcing. Building the training corpora manually is a costly enterprise which requires a lot of time and human resources. We propose to automate the process of corpus extension by integrating automatically obtained synonyms and paraphrases. Our methodology allowed us to significantly increase the size of the training corpus and its level of variability (the number of distinct tokens and specific syntactic structures). Our extension solutions are fully automatic and require only some initial validation. The human evaluation results confirm that in many cases native speakers favor the outputs of the model built on the extended corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="manishina-etal-2016-automatic">
<titleInfo>
<title>Automatic Corpus Extension for Data-driven Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Manishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bassam</namePart>
<namePart type="family">Jabaian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stéphane</namePart>
<namePart type="family">Huet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrice</namePart>
<namePart type="family">Lefèvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent. Corpus creation and extension in data-driven NLG domain traditionally involved manual paraphrasing performed by either a group of experts or with resort to crowd-sourcing. Building the training corpora manually is a costly enterprise which requires a lot of time and human resources. We propose to automate the process of corpus extension by integrating automatically obtained synonyms and paraphrases. Our methodology allowed us to significantly increase the size of the training corpus and its level of variability (the number of distinct tokens and specific syntactic structures). Our extension solutions are fully automatic and require only some initial validation. The human evaluation results confirm that in many cases native speakers favor the outputs of the model built on the extended corpus.</abstract>
<identifier type="citekey">manishina-etal-2016-automatic</identifier>
<location>
<url>https://aclanthology.org/L16-1575/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3624</start>
<end>3631</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Corpus Extension for Data-driven Natural Language Generation
%A Manishina, Elena
%A Jabaian, Bassam
%A Huet, Stéphane
%A Lefèvre, Fabrice
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F manishina-etal-2016-automatic
%X As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent. Corpus creation and extension in data-driven NLG domain traditionally involved manual paraphrasing performed by either a group of experts or with resort to crowd-sourcing. Building the training corpora manually is a costly enterprise which requires a lot of time and human resources. We propose to automate the process of corpus extension by integrating automatically obtained synonyms and paraphrases. Our methodology allowed us to significantly increase the size of the training corpus and its level of variability (the number of distinct tokens and specific syntactic structures). Our extension solutions are fully automatic and require only some initial validation. The human evaluation results confirm that in many cases native speakers favor the outputs of the model built on the extended corpus.
%U https://aclanthology.org/L16-1575/
%P 3624-3631
Markdown (Informal)
[Automatic Corpus Extension for Data-driven Natural Language Generation](https://aclanthology.org/L16-1575/) (Manishina et al., LREC 2016)
ACL