@inproceedings{kolesnichenko-etal-2023-word,
title = "Word Substitution with Masked Language Models as Data Augmentation for Sentiment Analysis",
author = "Kolesnichenko, Larisa and
Velldal, Erik and
{\O}vrelid, Lilja",
editor = "Ilinykh, Nikolai and
Morger, Felix and
Dann{\'e}lls, Dana and
Dobnik, Simon and
Megyesi, Be{\'a}ta and
Nivre, Joakim",
booktitle = "Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)",
month = may,
year = "2023",
address = "T{\'o}rshavn, the Faroe Islands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.resourceful-1.6",
pages = "42--47",
abstract = "This paper explores the use of masked language modeling (MLM) for data augmentation (DA), targeting structured sentiment analysis (SSA) for Norwegian based on a dataset of annotated reviews. Considering the limited resources for Norwegian language and the complexity of the annotation task, the aim is to investigate whether this approach to data augmentation can help boost the performance. We report on experiments with substituting words both inside and outside of sentiment annotations, and we also present an error analysis, discussing some of the potential pitfalls of using MLM-based DA for SSA, and suggest directions for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolesnichenko-etal-2023-word">
<titleInfo>
<title>Word Substitution with Masked Language Models as Data Augmentation for Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Larisa</namePart>
<namePart type="family">Kolesnichenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Velldal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beáta</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tórshavn, the Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the use of masked language modeling (MLM) for data augmentation (DA), targeting structured sentiment analysis (SSA) for Norwegian based on a dataset of annotated reviews. Considering the limited resources for Norwegian language and the complexity of the annotation task, the aim is to investigate whether this approach to data augmentation can help boost the performance. We report on experiments with substituting words both inside and outside of sentiment annotations, and we also present an error analysis, discussing some of the potential pitfalls of using MLM-based DA for SSA, and suggest directions for future work.</abstract>
<identifier type="citekey">kolesnichenko-etal-2023-word</identifier>
<location>
<url>https://aclanthology.org/2023.resourceful-1.6</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>42</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Substitution with Masked Language Models as Data Augmentation for Sentiment Analysis
%A Kolesnichenko, Larisa
%A Velldal, Erik
%A Øvrelid, Lilja
%Y Ilinykh, Nikolai
%Y Morger, Felix
%Y Dannélls, Dana
%Y Dobnik, Simon
%Y Megyesi, Beáta
%Y Nivre, Joakim
%S Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Tórshavn, the Faroe Islands
%F kolesnichenko-etal-2023-word
%X This paper explores the use of masked language modeling (MLM) for data augmentation (DA), targeting structured sentiment analysis (SSA) for Norwegian based on a dataset of annotated reviews. Considering the limited resources for Norwegian language and the complexity of the annotation task, the aim is to investigate whether this approach to data augmentation can help boost the performance. We report on experiments with substituting words both inside and outside of sentiment annotations, and we also present an error analysis, discussing some of the potential pitfalls of using MLM-based DA for SSA, and suggest directions for future work.
%U https://aclanthology.org/2023.resourceful-1.6
%P 42-47
Markdown (Informal)
[Word Substitution with Masked Language Models as Data Augmentation for Sentiment Analysis](https://aclanthology.org/2023.resourceful-1.6) (Kolesnichenko et al., RESOURCEFUL 2023)
ACL