@inproceedings{butnaru-ionescu-2018-unibuckernel,
title = "{U}nibuc{K}ernel: A kernel-based learning method for complex word identification",
author = "Butnaru, Andrei and
Ionescu, Radu Tudor",
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/W18-0519",
doi = "10.18653/v1/W18-0519",
pages = "175--183",
abstract = "In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic features that are either automatically learned using word embeddings or extracted from a lexical knowledge base, namely WordNet. After feature extraction, we employ a kernel method for the learning phase. The feature matrix is first transformed into a normalized kernel matrix. For the binary classification task (simple versus complex), we employ Support Vector Machines. For the regression task, in which we have to predict the complexity level of a word (a word is more complex if it is labeled as complex by more annotators), we employ v-Support Vector Regression. We applied our approach only on the three English data sets containing documents from Wikipedia, WikiNews and News domains. Our best result during the competition was the third place on the English Wikipedia data set. However, in this paper, we also report better post-competition results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="butnaru-ionescu-2018-unibuckernel">
<titleInfo>
<title>UnibucKernel: A kernel-based learning method for complex word identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Butnaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="given">Tudor</namePart>
<namePart type="family">Ionescu</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>In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic features that are either automatically learned using word embeddings or extracted from a lexical knowledge base, namely WordNet. After feature extraction, we employ a kernel method for the learning phase. The feature matrix is first transformed into a normalized kernel matrix. For the binary classification task (simple versus complex), we employ Support Vector Machines. For the regression task, in which we have to predict the complexity level of a word (a word is more complex if it is labeled as complex by more annotators), we employ v-Support Vector Regression. We applied our approach only on the three English data sets containing documents from Wikipedia, WikiNews and News domains. Our best result during the competition was the third place on the English Wikipedia data set. However, in this paper, we also report better post-competition results.</abstract>
<identifier type="citekey">butnaru-ionescu-2018-unibuckernel</identifier>
<identifier type="doi">10.18653/v1/W18-0519</identifier>
<location>
<url>https://aclanthology.org/W18-0519</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>175</start>
<end>183</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UnibucKernel: A kernel-based learning method for complex word identification
%A Butnaru, Andrei
%A Ionescu, Radu Tudor
%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 butnaru-ionescu-2018-unibuckernel
%X In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task. Our approach is based on combining multiple low-level features, such as character n-grams, with high-level semantic features that are either automatically learned using word embeddings or extracted from a lexical knowledge base, namely WordNet. After feature extraction, we employ a kernel method for the learning phase. The feature matrix is first transformed into a normalized kernel matrix. For the binary classification task (simple versus complex), we employ Support Vector Machines. For the regression task, in which we have to predict the complexity level of a word (a word is more complex if it is labeled as complex by more annotators), we employ v-Support Vector Regression. We applied our approach only on the three English data sets containing documents from Wikipedia, WikiNews and News domains. Our best result during the competition was the third place on the English Wikipedia data set. However, in this paper, we also report better post-competition results.
%R 10.18653/v1/W18-0519
%U https://aclanthology.org/W18-0519
%U https://doi.org/10.18653/v1/W18-0519
%P 175-183
Markdown (Informal)
[UnibucKernel: A kernel-based learning method for complex word identification](https://aclanthology.org/W18-0519) (Butnaru & Ionescu, BEA 2018)
ACL