@inproceedings{aguirre-etal-2022-exploiting,
title = "Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in {NLU} of Intra-Sentential Code-Switching Chatbot Interactions",
author = "Aguirre, Maia and
Serras, Manex and
Garc{\'\i}a-sardi{\~n}a, Laura and
L{\'o}pez-fern{\'a}ndez, Jacobo and
M{\'e}ndez, Ariane and
Del Pozo, Arantza",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.13",
doi = "10.18653/v1/2022.emnlp-industry.13",
pages = "138--144",
abstract = "Code-switching (CS) is a very common phenomenon in regions with various co-existing languages. Since CS is such a frequent habit in informal communications, both spoken and written, it also arises naturally in Human-Machine Interactions. Therefore, in order for natural language understanding (NLU) not to be degraded, CS must be taken into account when developing chatbots. The co-existence of multiple languages in a single NLU model has become feasible with multilingual language representation models such as mBERT. In this paper, the efficacy of zero-shot cross-lingual transfer learning with mBERT for NLU is evaluated on a Basque-Spanish CS chatbot corpus, comparing the performance of NLU models trained using in-domain chatbot utterances in Basque and/or Spanish without CS. The results obtained indicate that training joint multi-intent classification and entity recognition models on both languages simultaneously achieves best performance, better capturing the CS patterns.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aguirre-etal-2022-exploiting">
<titleInfo>
<title>Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in NLU of Intra-Sentential Code-Switching Chatbot Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maia</namePart>
<namePart type="family">Aguirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manex</namePart>
<namePart type="family">Serras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">García-sardiña</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacobo</namePart>
<namePart type="family">López-fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariane</namePart>
<namePart type="family">Méndez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arantza</namePart>
<namePart type="family">Del Pozo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-switching (CS) is a very common phenomenon in regions with various co-existing languages. Since CS is such a frequent habit in informal communications, both spoken and written, it also arises naturally in Human-Machine Interactions. Therefore, in order for natural language understanding (NLU) not to be degraded, CS must be taken into account when developing chatbots. The co-existence of multiple languages in a single NLU model has become feasible with multilingual language representation models such as mBERT. In this paper, the efficacy of zero-shot cross-lingual transfer learning with mBERT for NLU is evaluated on a Basque-Spanish CS chatbot corpus, comparing the performance of NLU models trained using in-domain chatbot utterances in Basque and/or Spanish without CS. The results obtained indicate that training joint multi-intent classification and entity recognition models on both languages simultaneously achieves best performance, better capturing the CS patterns.</abstract>
<identifier type="citekey">aguirre-etal-2022-exploiting</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.13</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.13</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>138</start>
<end>144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in NLU of Intra-Sentential Code-Switching Chatbot Interactions
%A Aguirre, Maia
%A Serras, Manex
%A García-sardiña, Laura
%A López-fernández, Jacobo
%A Méndez, Ariane
%A Del Pozo, Arantza
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F aguirre-etal-2022-exploiting
%X Code-switching (CS) is a very common phenomenon in regions with various co-existing languages. Since CS is such a frequent habit in informal communications, both spoken and written, it also arises naturally in Human-Machine Interactions. Therefore, in order for natural language understanding (NLU) not to be degraded, CS must be taken into account when developing chatbots. The co-existence of multiple languages in a single NLU model has become feasible with multilingual language representation models such as mBERT. In this paper, the efficacy of zero-shot cross-lingual transfer learning with mBERT for NLU is evaluated on a Basque-Spanish CS chatbot corpus, comparing the performance of NLU models trained using in-domain chatbot utterances in Basque and/or Spanish without CS. The results obtained indicate that training joint multi-intent classification and entity recognition models on both languages simultaneously achieves best performance, better capturing the CS patterns.
%R 10.18653/v1/2022.emnlp-industry.13
%U https://aclanthology.org/2022.emnlp-industry.13
%U https://doi.org/10.18653/v1/2022.emnlp-industry.13
%P 138-144
Markdown (Informal)
[Exploiting In-Domain Bilingual Corpora for Zero-Shot Transfer Learning in NLU of Intra-Sentential Code-Switching Chatbot Interactions](https://aclanthology.org/2022.emnlp-industry.13) (Aguirre et al., EMNLP 2022)
ACL