@inproceedings{ramanarayanan-pugh-2018-automatic,
title = "Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora",
author = "Ramanarayanan, Vikram and
Pugh, Robert",
editor = "Komatani, Kazunori and
Litman, Diane and
Yu, Kai and
Papangelis, Alex and
Cavedon, Lawrence and
Nakano, Mikio",
booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5009",
doi = "10.18653/v1/W18-5009",
pages = "80--88",
abstract = "We examine the efficacy of various feature{--}learner combinations for language identification in different types of text-based code-switched interactions {--} human-human dialog, human-machine dialog as well as monolog {--} at both the token and turn levels. In order to examine the generalization of such methods across language pairs and datasets, we analyze 10 different datasets of code-switched text. We extract a variety of character- and word-based text features and pass them into multiple learners, including conditional random fields, logistic regressors and recurrent neural networks. We further examine the efficacy of novel character-level embedding and GloVe features in improving performance and observe that our best-performing text system significantly outperforms a majority vote baseline across language pairs and datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramanarayanan-pugh-2018-automatic">
<titleInfo>
<title>Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vikram</namePart>
<namePart type="family">Ramanarayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Cavedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We examine the efficacy of various feature–learner combinations for language identification in different types of text-based code-switched interactions – human-human dialog, human-machine dialog as well as monolog – at both the token and turn levels. In order to examine the generalization of such methods across language pairs and datasets, we analyze 10 different datasets of code-switched text. We extract a variety of character- and word-based text features and pass them into multiple learners, including conditional random fields, logistic regressors and recurrent neural networks. We further examine the efficacy of novel character-level embedding and GloVe features in improving performance and observe that our best-performing text system significantly outperforms a majority vote baseline across language pairs and datasets.</abstract>
<identifier type="citekey">ramanarayanan-pugh-2018-automatic</identifier>
<identifier type="doi">10.18653/v1/W18-5009</identifier>
<location>
<url>https://aclanthology.org/W18-5009</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>80</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora
%A Ramanarayanan, Vikram
%A Pugh, Robert
%Y Komatani, Kazunori
%Y Litman, Diane
%Y Yu, Kai
%Y Papangelis, Alex
%Y Cavedon, Lawrence
%Y Nakano, Mikio
%S Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F ramanarayanan-pugh-2018-automatic
%X We examine the efficacy of various feature–learner combinations for language identification in different types of text-based code-switched interactions – human-human dialog, human-machine dialog as well as monolog – at both the token and turn levels. In order to examine the generalization of such methods across language pairs and datasets, we analyze 10 different datasets of code-switched text. We extract a variety of character- and word-based text features and pass them into multiple learners, including conditional random fields, logistic regressors and recurrent neural networks. We further examine the efficacy of novel character-level embedding and GloVe features in improving performance and observe that our best-performing text system significantly outperforms a majority vote baseline across language pairs and datasets.
%R 10.18653/v1/W18-5009
%U https://aclanthology.org/W18-5009
%U https://doi.org/10.18653/v1/W18-5009
%P 80-88
Markdown (Informal)
[Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora](https://aclanthology.org/W18-5009) (Ramanarayanan & Pugh, SIGDIAL 2018)
ACL