@inproceedings{calvillo-etal-2020-surprisal,
title = "Surprisal Predicts Code-Switching in {C}hinese-{E}nglish Bilingual Text",
author = "Calvillo, Jes{\'u}s and
Fang, Le and
Cole, Jeremy and
Reitter, David",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.330",
doi = "10.18653/v1/2020.emnlp-main.330",
pages = "4029--4039",
abstract = "Why do bilinguals switch languages within a sentence? The present observational study asks whether word surprisal and word entropy predict code-switching in bilingual written conversation. We describe and model a new dataset of Chinese-English text with 1476 clean code-switched sentences, translated back into Chinese. The model includes known control variables together with word surprisal and word entropy. We found that word surprisal, but not entropy, is a significant predictor that explains code-switching above and beyond other well-known predictors. We also found sentence length to be a significant predictor, which has been related to sentence complexity. We propose high cognitive effort as a reason for code-switching, as it leaves fewer resources for inhibition of the alternative language. We also corroborate previous findings, but this time using a computational model of surprisal, a new language pair, and doing so for written language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calvillo-etal-2020-surprisal">
<titleInfo>
<title>Surprisal Predicts Code-Switching in Chinese-English Bilingual Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesús</namePart>
<namePart type="family">Calvillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Cole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Why do bilinguals switch languages within a sentence? The present observational study asks whether word surprisal and word entropy predict code-switching in bilingual written conversation. We describe and model a new dataset of Chinese-English text with 1476 clean code-switched sentences, translated back into Chinese. The model includes known control variables together with word surprisal and word entropy. We found that word surprisal, but not entropy, is a significant predictor that explains code-switching above and beyond other well-known predictors. We also found sentence length to be a significant predictor, which has been related to sentence complexity. We propose high cognitive effort as a reason for code-switching, as it leaves fewer resources for inhibition of the alternative language. We also corroborate previous findings, but this time using a computational model of surprisal, a new language pair, and doing so for written language.</abstract>
<identifier type="citekey">calvillo-etal-2020-surprisal</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.330</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.330</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4029</start>
<end>4039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Surprisal Predicts Code-Switching in Chinese-English Bilingual Text
%A Calvillo, Jesús
%A Fang, Le
%A Cole, Jeremy
%A Reitter, David
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F calvillo-etal-2020-surprisal
%X Why do bilinguals switch languages within a sentence? The present observational study asks whether word surprisal and word entropy predict code-switching in bilingual written conversation. We describe and model a new dataset of Chinese-English text with 1476 clean code-switched sentences, translated back into Chinese. The model includes known control variables together with word surprisal and word entropy. We found that word surprisal, but not entropy, is a significant predictor that explains code-switching above and beyond other well-known predictors. We also found sentence length to be a significant predictor, which has been related to sentence complexity. We propose high cognitive effort as a reason for code-switching, as it leaves fewer resources for inhibition of the alternative language. We also corroborate previous findings, but this time using a computational model of surprisal, a new language pair, and doing so for written language.
%R 10.18653/v1/2020.emnlp-main.330
%U https://aclanthology.org/2020.emnlp-main.330
%U https://doi.org/10.18653/v1/2020.emnlp-main.330
%P 4029-4039
Markdown (Informal)
[Surprisal Predicts Code-Switching in Chinese-English Bilingual Text](https://aclanthology.org/2020.emnlp-main.330) (Calvillo et al., EMNLP 2020)
ACL