@inproceedings{winkler-etal-2024-slot,
title = "Slot and Intent Detection Resources for {B}avarian and {L}ithuanian: Assessing Translations vs Natural Queries to Digital Assistants",
author = "Winkler, Miriam and
Juozapaityte, Virginija and
van der Goot, Rob and
Plank, Barbara",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1297/",
pages = "14898--14915",
abstract = "Digital assistants perform well in high-resource languages like English, where tasks like slot and intent detection (SID) are well-supported. Many recent SID datasets start including multiple language varieties. However, it is unclear how realistic these translated datasets are. Therefore, we extend one such dataset, namely xSID-0.4, to include two underrepresented languages: Bavarian, a German dialect, and Lithuanian, a Baltic language. Both language variants have limited speaker populations and are often not included in multilingual projects. In addition to translations we provide {\textquotedblleft}natural{\textquotedblright} queries to digital assistants generated by native speakers. We further include utterances from another dataset for Bavarian to build the richest SID dataset available today for a low-resource dialect without standard orthography. We then set out to evaluate models trained on English in a zero-shot scenario on our target language variants. Our evaluation reveals that translated data can produce overly optimistic scores. However, the error patterns in translated and natural datasets are highly similar. Cross-dataset experiments demonstrate that data collection methods influence performance, with scores lower than those achieved with single-dataset translations. This work contributes to enhancing SID datasets for underrepresented languages, yielding NaLiBaSID, a new evaluation dataset for Bavarian and Lithuanian."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winkler-etal-2024-slot">
<titleInfo>
<title>Slot and Intent Detection Resources for Bavarian and Lithuanian: Assessing Translations vs Natural Queries to Digital Assistants</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Winkler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Virginija</namePart>
<namePart type="family">Juozapaityte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Digital assistants perform well in high-resource languages like English, where tasks like slot and intent detection (SID) are well-supported. Many recent SID datasets start including multiple language varieties. However, it is unclear how realistic these translated datasets are. Therefore, we extend one such dataset, namely xSID-0.4, to include two underrepresented languages: Bavarian, a German dialect, and Lithuanian, a Baltic language. Both language variants have limited speaker populations and are often not included in multilingual projects. In addition to translations we provide “natural” queries to digital assistants generated by native speakers. We further include utterances from another dataset for Bavarian to build the richest SID dataset available today for a low-resource dialect without standard orthography. We then set out to evaluate models trained on English in a zero-shot scenario on our target language variants. Our evaluation reveals that translated data can produce overly optimistic scores. However, the error patterns in translated and natural datasets are highly similar. Cross-dataset experiments demonstrate that data collection methods influence performance, with scores lower than those achieved with single-dataset translations. This work contributes to enhancing SID datasets for underrepresented languages, yielding NaLiBaSID, a new evaluation dataset for Bavarian and Lithuanian.</abstract>
<identifier type="citekey">winkler-etal-2024-slot</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1297/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14898</start>
<end>14915</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Slot and Intent Detection Resources for Bavarian and Lithuanian: Assessing Translations vs Natural Queries to Digital Assistants
%A Winkler, Miriam
%A Juozapaityte, Virginija
%A van der Goot, Rob
%A Plank, Barbara
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F winkler-etal-2024-slot
%X Digital assistants perform well in high-resource languages like English, where tasks like slot and intent detection (SID) are well-supported. Many recent SID datasets start including multiple language varieties. However, it is unclear how realistic these translated datasets are. Therefore, we extend one such dataset, namely xSID-0.4, to include two underrepresented languages: Bavarian, a German dialect, and Lithuanian, a Baltic language. Both language variants have limited speaker populations and are often not included in multilingual projects. In addition to translations we provide “natural” queries to digital assistants generated by native speakers. We further include utterances from another dataset for Bavarian to build the richest SID dataset available today for a low-resource dialect without standard orthography. We then set out to evaluate models trained on English in a zero-shot scenario on our target language variants. Our evaluation reveals that translated data can produce overly optimistic scores. However, the error patterns in translated and natural datasets are highly similar. Cross-dataset experiments demonstrate that data collection methods influence performance, with scores lower than those achieved with single-dataset translations. This work contributes to enhancing SID datasets for underrepresented languages, yielding NaLiBaSID, a new evaluation dataset for Bavarian and Lithuanian.
%U https://aclanthology.org/2024.lrec-main.1297/
%P 14898-14915
Markdown (Informal)
[Slot and Intent Detection Resources for Bavarian and Lithuanian: Assessing Translations vs Natural Queries to Digital Assistants](https://aclanthology.org/2024.lrec-main.1297/) (Winkler et al., LREC-COLING 2024)
ACL