@inproceedings{shardlow-etal-2020-complex,
title = "{C}omp{L}ex {---} A New Corpus for Lexical Complexity Prediction from {L}ikert {S}cale Data",
author = "Shardlow, Matthew and
Cooper, Michael and
Zampieri, Marcos",
editor = "Gala, N{\'u}ria and
Wilkens, Rodrigo",
booktitle = "Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.readi-1.9",
pages = "57--62",
abstract = "Predicting which words are considered hard to understand for a given target population is a vital step in many NLP applications such astext simplification. This task is commonly referred to as Complex Word Identification (CWI). With a few exceptions, previous studieshave approached the task as a binary classification task in which systems predict a complexity value (complex vs. non-complex) fora set of target words in a text. This choice is motivated by the fact that all CWI datasets compiled so far have been annotated using abinary annotation scheme. Our paper addresses this limitation by presenting the first English dataset for continuous lexical complexityprediction. We use a 5-point Likert scale scheme to annotate complex words in texts from three sources/domains: the Bible, Europarl,and biomedical texts. This resulted in a corpus of 9,476 sentences each annotated by around 7 annotators.",
language = "English",
ISBN = "979-10-95546-45-0",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shardlow-etal-2020-complex">
<titleInfo>
<title>CompLex — A New Corpus for Lexical Complexity Prediction from Likert Scale Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Cooper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Gala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-45-0</identifier>
</relatedItem>
<abstract>Predicting which words are considered hard to understand for a given target population is a vital step in many NLP applications such astext simplification. This task is commonly referred to as Complex Word Identification (CWI). With a few exceptions, previous studieshave approached the task as a binary classification task in which systems predict a complexity value (complex vs. non-complex) fora set of target words in a text. This choice is motivated by the fact that all CWI datasets compiled so far have been annotated using abinary annotation scheme. Our paper addresses this limitation by presenting the first English dataset for continuous lexical complexityprediction. We use a 5-point Likert scale scheme to annotate complex words in texts from three sources/domains: the Bible, Europarl,and biomedical texts. This resulted in a corpus of 9,476 sentences each annotated by around 7 annotators.</abstract>
<identifier type="citekey">shardlow-etal-2020-complex</identifier>
<location>
<url>https://aclanthology.org/2020.readi-1.9</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>57</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CompLex — A New Corpus for Lexical Complexity Prediction from Likert Scale Data
%A Shardlow, Matthew
%A Cooper, Michael
%A Zampieri, Marcos
%Y Gala, Núria
%Y Wilkens, Rodrigo
%S Proceedings of the 1st Workshop on Tools and Resources to Empower People with REAding DIfficulties (READI)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-45-0
%G English
%F shardlow-etal-2020-complex
%X Predicting which words are considered hard to understand for a given target population is a vital step in many NLP applications such astext simplification. This task is commonly referred to as Complex Word Identification (CWI). With a few exceptions, previous studieshave approached the task as a binary classification task in which systems predict a complexity value (complex vs. non-complex) fora set of target words in a text. This choice is motivated by the fact that all CWI datasets compiled so far have been annotated using abinary annotation scheme. Our paper addresses this limitation by presenting the first English dataset for continuous lexical complexityprediction. We use a 5-point Likert scale scheme to annotate complex words in texts from three sources/domains: the Bible, Europarl,and biomedical texts. This resulted in a corpus of 9,476 sentences each annotated by around 7 annotators.
%U https://aclanthology.org/2020.readi-1.9
%P 57-62
Markdown (Informal)
[CompLex — A New Corpus for Lexical Complexity Prediction from Likert Scale Data](https://aclanthology.org/2020.readi-1.9) (Shardlow et al., READI 2020)
ACL