@inproceedings{samanta-etal-2019-improved,
title = "Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text",
author = "Samanta, Bidisha and
Ganguly, Niloy and
Chakrabarti, Soumen",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1343",
doi = "10.18653/v1/P19-1343",
pages = "3528--3537",
abstract = "Multilingual writers and speakers often alternate between two languages in a single discourse. This practice is called {``}code-switching{''}. Existing sentiment detection methods are usually trained on sentiment-labeled monolingual text. Manually labeled code-switched text, especially involving minority languages, is extremely rare. Consequently, the best monolingual methods perform relatively poorly on code-switched text. We present an effective technique for synthesizing labeled code-switched text from labeled monolingual text, which is relatively readily available. The idea is to replace carefully selected subtrees of constituency parses of sentences in the resource-rich language with suitable token spans selected from automatic translations to the resource-poor language. By augmenting the scarce labeled code-switched text with plentiful synthetic labeled code-switched text, we achieve significant improvements in sentiment labeling accuracy (1.5{\%}, 5.11{\%} 7.20{\%}) for three different language pairs (English-Hindi, English-Spanish and English-Bengali). The improvement is even significant in hatespeech detection whereby we achieve a 4{\%} improvement using only synthetic code-switched data (6{\%} with data augmentation).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samanta-etal-2019-improved">
<titleInfo>
<title>Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bidisha</namePart>
<namePart type="family">Samanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Chakrabarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual writers and speakers often alternate between two languages in a single discourse. This practice is called “code-switching”. Existing sentiment detection methods are usually trained on sentiment-labeled monolingual text. Manually labeled code-switched text, especially involving minority languages, is extremely rare. Consequently, the best monolingual methods perform relatively poorly on code-switched text. We present an effective technique for synthesizing labeled code-switched text from labeled monolingual text, which is relatively readily available. The idea is to replace carefully selected subtrees of constituency parses of sentences in the resource-rich language with suitable token spans selected from automatic translations to the resource-poor language. By augmenting the scarce labeled code-switched text with plentiful synthetic labeled code-switched text, we achieve significant improvements in sentiment labeling accuracy (1.5%, 5.11% 7.20%) for three different language pairs (English-Hindi, English-Spanish and English-Bengali). The improvement is even significant in hatespeech detection whereby we achieve a 4% improvement using only synthetic code-switched data (6% with data augmentation).</abstract>
<identifier type="citekey">samanta-etal-2019-improved</identifier>
<identifier type="doi">10.18653/v1/P19-1343</identifier>
<location>
<url>https://aclanthology.org/P19-1343</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3528</start>
<end>3537</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text
%A Samanta, Bidisha
%A Ganguly, Niloy
%A Chakrabarti, Soumen
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F samanta-etal-2019-improved
%X Multilingual writers and speakers often alternate between two languages in a single discourse. This practice is called “code-switching”. Existing sentiment detection methods are usually trained on sentiment-labeled monolingual text. Manually labeled code-switched text, especially involving minority languages, is extremely rare. Consequently, the best monolingual methods perform relatively poorly on code-switched text. We present an effective technique for synthesizing labeled code-switched text from labeled monolingual text, which is relatively readily available. The idea is to replace carefully selected subtrees of constituency parses of sentences in the resource-rich language with suitable token spans selected from automatic translations to the resource-poor language. By augmenting the scarce labeled code-switched text with plentiful synthetic labeled code-switched text, we achieve significant improvements in sentiment labeling accuracy (1.5%, 5.11% 7.20%) for three different language pairs (English-Hindi, English-Spanish and English-Bengali). The improvement is even significant in hatespeech detection whereby we achieve a 4% improvement using only synthetic code-switched data (6% with data augmentation).
%R 10.18653/v1/P19-1343
%U https://aclanthology.org/P19-1343
%U https://doi.org/10.18653/v1/P19-1343
%P 3528-3537
Markdown (Informal)
[Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text](https://aclanthology.org/P19-1343) (Samanta et al., ACL 2019)
ACL