@inproceedings{pattichis-etal-2023-code,
title = "Code-Switching Metrics Using Intonation Units",
author = "Pattichis, Rebecca and
LaCasse, Dora and
Trawick, Sonya and
Cacoullos, Rena",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.1047",
doi = "10.18653/v1/2023.emnlp-main.1047",
pages = "16840--16849",
abstract = "Code-switching (CS) metrics in NLP that are based on word-level units are misaligned with true bilingual CS behavior. Crucially, CS is not equally likely between any two words, but follows syntactic and prosodic rules. We adapt two metrics, multilinguality and CS probability, and apply them to transcribed bilingual speech, for the first time putting forward Intonation Units (IUs) {--} prosodic speech segments {--} as basic tokens for NLP tasks. In addition, we calculate these two metrics separately for distinct mixing types: alternating-language multi-word strings and single-word incorporations from one language into another. Results indicate that individual differences according to the two CS metrics are independent. However, there is a shared tendency among bilinguals for multi-word CS to occur across, rather than within, IU boundaries. That is, bilinguals tend to prosodically separate their two languages. This constraint is blurred when metric calculations do not distinguish multi-word and single-word items. These results call for a reconsideration of units of analysis in future development of CS datasets for NLP tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pattichis-etal-2023-code">
<titleInfo>
<title>Code-Switching Metrics Using Intonation Units</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Pattichis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dora</namePart>
<namePart type="family">LaCasse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonya</namePart>
<namePart type="family">Trawick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rena</namePart>
<namePart type="family">Cacoullos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-switching (CS) metrics in NLP that are based on word-level units are misaligned with true bilingual CS behavior. Crucially, CS is not equally likely between any two words, but follows syntactic and prosodic rules. We adapt two metrics, multilinguality and CS probability, and apply them to transcribed bilingual speech, for the first time putting forward Intonation Units (IUs) – prosodic speech segments – as basic tokens for NLP tasks. In addition, we calculate these two metrics separately for distinct mixing types: alternating-language multi-word strings and single-word incorporations from one language into another. Results indicate that individual differences according to the two CS metrics are independent. However, there is a shared tendency among bilinguals for multi-word CS to occur across, rather than within, IU boundaries. That is, bilinguals tend to prosodically separate their two languages. This constraint is blurred when metric calculations do not distinguish multi-word and single-word items. These results call for a reconsideration of units of analysis in future development of CS datasets for NLP tasks.</abstract>
<identifier type="citekey">pattichis-etal-2023-code</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.1047</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.1047</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>16840</start>
<end>16849</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Switching Metrics Using Intonation Units
%A Pattichis, Rebecca
%A LaCasse, Dora
%A Trawick, Sonya
%A Cacoullos, Rena
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F pattichis-etal-2023-code
%X Code-switching (CS) metrics in NLP that are based on word-level units are misaligned with true bilingual CS behavior. Crucially, CS is not equally likely between any two words, but follows syntactic and prosodic rules. We adapt two metrics, multilinguality and CS probability, and apply them to transcribed bilingual speech, for the first time putting forward Intonation Units (IUs) – prosodic speech segments – as basic tokens for NLP tasks. In addition, we calculate these two metrics separately for distinct mixing types: alternating-language multi-word strings and single-word incorporations from one language into another. Results indicate that individual differences according to the two CS metrics are independent. However, there is a shared tendency among bilinguals for multi-word CS to occur across, rather than within, IU boundaries. That is, bilinguals tend to prosodically separate their two languages. This constraint is blurred when metric calculations do not distinguish multi-word and single-word items. These results call for a reconsideration of units of analysis in future development of CS datasets for NLP tasks.
%R 10.18653/v1/2023.emnlp-main.1047
%U https://aclanthology.org/2023.emnlp-main.1047
%U https://doi.org/10.18653/v1/2023.emnlp-main.1047
%P 16840-16849
Markdown (Informal)
[Code-Switching Metrics Using Intonation Units](https://aclanthology.org/2023.emnlp-main.1047) (Pattichis et al., EMNLP 2023)
ACL
- Rebecca Pattichis, Dora LaCasse, Sonya Trawick, and Rena Cacoullos. 2023. Code-Switching Metrics Using Intonation Units. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16840–16849, Singapore. Association for Computational Linguistics.