@inproceedings{aburaed-saggion-2018-lastus,
title = "{L}a{STUS}/{TALN} at Complex Word Identification ({CWI}) 2018 Shared Task",
author = "AbuRa{'}ed, Ahmed and
Saggion, Horacio",
editor = "Tetreault, Joel and
Burstein, Jill and
Kochmar, Ekaterina and
Leacock, Claudia and
Yannakoudakis, Helen",
booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-0517",
doi = "10.18653/v1/W18-0517",
pages = "159--165",
abstract = "This paper presents the participation of the LaSTUS/TALN team in the Complex Word Identification (CWI) Shared Task 2018 in the English monolingual track . The purpose of the task was to determine if a word in a given sentence can be judged as complex or not by a certain target audience. For the English track, task organizers provided a training and a development datasets of 27,299 and 3,328 words respectively together with the sentence in which each word occurs. The words were judged as complex or not by 20 human evaluators; ten of whom are natives. We submitted two systems: one system modeled each word to evaluate as a numeric vector populated with a set of lexical, semantic and contextual features while the other system relies on a word embedding representation and a distance metric. We trained two separate classifiers to automatically decide if each word is complex or not. We submitted six runs, two for each of the three subsets of the English monolingual CWI track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aburaed-saggion-2018-lastus">
<titleInfo>
<title>LaSTUS/TALN at Complex Word Identification (CWI) 2018 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">AbuRa’ed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the participation of the LaSTUS/TALN team in the Complex Word Identification (CWI) Shared Task 2018 in the English monolingual track . The purpose of the task was to determine if a word in a given sentence can be judged as complex or not by a certain target audience. For the English track, task organizers provided a training and a development datasets of 27,299 and 3,328 words respectively together with the sentence in which each word occurs. The words were judged as complex or not by 20 human evaluators; ten of whom are natives. We submitted two systems: one system modeled each word to evaluate as a numeric vector populated with a set of lexical, semantic and contextual features while the other system relies on a word embedding representation and a distance metric. We trained two separate classifiers to automatically decide if each word is complex or not. We submitted six runs, two for each of the three subsets of the English monolingual CWI track.</abstract>
<identifier type="citekey">aburaed-saggion-2018-lastus</identifier>
<identifier type="doi">10.18653/v1/W18-0517</identifier>
<location>
<url>https://aclanthology.org/W18-0517</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>159</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LaSTUS/TALN at Complex Word Identification (CWI) 2018 Shared Task
%A AbuRa’ed, Ahmed
%A Saggion, Horacio
%Y Tetreault, Joel
%Y Burstein, Jill
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Yannakoudakis, Helen
%S Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F aburaed-saggion-2018-lastus
%X This paper presents the participation of the LaSTUS/TALN team in the Complex Word Identification (CWI) Shared Task 2018 in the English monolingual track . The purpose of the task was to determine if a word in a given sentence can be judged as complex or not by a certain target audience. For the English track, task organizers provided a training and a development datasets of 27,299 and 3,328 words respectively together with the sentence in which each word occurs. The words were judged as complex or not by 20 human evaluators; ten of whom are natives. We submitted two systems: one system modeled each word to evaluate as a numeric vector populated with a set of lexical, semantic and contextual features while the other system relies on a word embedding representation and a distance metric. We trained two separate classifiers to automatically decide if each word is complex or not. We submitted six runs, two for each of the three subsets of the English monolingual CWI track.
%R 10.18653/v1/W18-0517
%U https://aclanthology.org/W18-0517
%U https://doi.org/10.18653/v1/W18-0517
%P 159-165
Markdown (Informal)
[LaSTUS/TALN at Complex Word Identification (CWI) 2018 Shared Task](https://aclanthology.org/W18-0517) (AbuRa’ed & Saggion, BEA 2018)
ACL