@inproceedings{costa-bertaglia-volpe-nunes-2016-exploring,
title = "Exploring Word Embeddings for Unsupervised Textual User-Generated Content Normalization",
author = "Costa Bertaglia, Thales Felipe and
Volpe Nunes, Maria das Gra\c cas",
editor = "Han, Bo and
Ritter, Alan and
Derczynski, Leon and
Xu, Wei and
Baldwin, Tim",
booktitle = "Proceedings of the 2nd Workshop on Noisy User-generated Text ({WNUT})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-3916/",
pages = "112--120",
abstract = "Text normalization techniques based on rules, lexicons or supervised training requiring large corpora are not scalable nor domain interchangeable, and this makes them unsuitable for normalizing user-generated content (UGC). Current tools available for Brazilian Portuguese make use of such techniques. In this work we propose a technique based on distributed representation of words (or word embeddings). It generates continuous numeric vectors of high-dimensionality to represent words. The vectors explicitly encode many linguistic regularities and patterns, as well as syntactic and semantic word relationships. Words that share semantic similarity are represented by similar vectors. Based on these features, we present a totally unsupervised, expandable and language and domain independent method for learning normalization lexicons from word embeddings. Our approach obtains high correction rate of orthographic errors and internet slang in product reviews, outperforming the current available tools for Brazilian Portuguese."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="costa-bertaglia-volpe-nunes-2016-exploring">
<titleInfo>
<title>Exploring Word Embeddings for Unsupervised Textual User-Generated Content Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thales</namePart>
<namePart type="given">Felipe</namePart>
<namePart type="family">Costa Bertaglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">das</namePart>
<namePart type="given">Gra\c</namePart>
<namePart type="given">cas</namePart>
<namePart type="family">Volpe Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text normalization techniques based on rules, lexicons or supervised training requiring large corpora are not scalable nor domain interchangeable, and this makes them unsuitable for normalizing user-generated content (UGC). Current tools available for Brazilian Portuguese make use of such techniques. In this work we propose a technique based on distributed representation of words (or word embeddings). It generates continuous numeric vectors of high-dimensionality to represent words. The vectors explicitly encode many linguistic regularities and patterns, as well as syntactic and semantic word relationships. Words that share semantic similarity are represented by similar vectors. Based on these features, we present a totally unsupervised, expandable and language and domain independent method for learning normalization lexicons from word embeddings. Our approach obtains high correction rate of orthographic errors and internet slang in product reviews, outperforming the current available tools for Brazilian Portuguese.</abstract>
<identifier type="citekey">costa-bertaglia-volpe-nunes-2016-exploring</identifier>
<location>
<url>https://aclanthology.org/W16-3916/</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>112</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Word Embeddings for Unsupervised Textual User-Generated Content Normalization
%A Costa Bertaglia, Thales Felipe
%A Volpe Nunes, Maria das Gra\c cas
%Y Han, Bo
%Y Ritter, Alan
%Y Derczynski, Leon
%Y Xu, Wei
%Y Baldwin, Tim
%S Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F costa-bertaglia-volpe-nunes-2016-exploring
%X Text normalization techniques based on rules, lexicons or supervised training requiring large corpora are not scalable nor domain interchangeable, and this makes them unsuitable for normalizing user-generated content (UGC). Current tools available for Brazilian Portuguese make use of such techniques. In this work we propose a technique based on distributed representation of words (or word embeddings). It generates continuous numeric vectors of high-dimensionality to represent words. The vectors explicitly encode many linguistic regularities and patterns, as well as syntactic and semantic word relationships. Words that share semantic similarity are represented by similar vectors. Based on these features, we present a totally unsupervised, expandable and language and domain independent method for learning normalization lexicons from word embeddings. Our approach obtains high correction rate of orthographic errors and internet slang in product reviews, outperforming the current available tools for Brazilian Portuguese.
%U https://aclanthology.org/W16-3916/
%P 112-120
Markdown (Informal)
[Exploring Word Embeddings for Unsupervised Textual User-Generated Content Normalization](https://aclanthology.org/W16-3916/) (Costa Bertaglia & Volpe Nunes, WNUT 2016)
ACL