@inproceedings{kanjirangat-etal-2022-early,
title = "Early Guessing for Dialect Identification",
author = "Kanjirangat, Vani and
Samardzic, Tanja and
Rinaldi, Fabio and
Dolamic, Ljiljana",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.479",
doi = "10.18653/v1/2022.findings-emnlp.479",
pages = "6417--6426",
abstract = "This paper deals with the problem of incre-mental dialect identification. Our goal is toreliably determine the dialect before the fullutterance is given as input. The major partof the previous research on dialect identification has been model-centric, focusing on performance. We address a new question: How much input is needed to identify a dialect? Ourapproach is a data-centric analysis that resultsin general criteria for finding the shortest inputneeded to make a plausible guess. Workingwith three sets of language dialects (Swiss German, Indo-Aryan and Arabic languages), weshow that it is possible to generalize across dialects and datasets with two input shorteningcriteria: model confidence and minimal inputlength (adjusted for the input type). The sourcecode for experimental analysis can be found atGithub.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanjirangat-etal-2022-early">
<titleInfo>
<title>Early Guessing for Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vani</namePart>
<namePart type="family">Kanjirangat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Samardzic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ljiljana</namePart>
<namePart type="family">Dolamic</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper deals with the problem of incre-mental dialect identification. Our goal is toreliably determine the dialect before the fullutterance is given as input. The major partof the previous research on dialect identification has been model-centric, focusing on performance. We address a new question: How much input is needed to identify a dialect? Ourapproach is a data-centric analysis that resultsin general criteria for finding the shortest inputneeded to make a plausible guess. Workingwith three sets of language dialects (Swiss German, Indo-Aryan and Arabic languages), weshow that it is possible to generalize across dialects and datasets with two input shorteningcriteria: model confidence and minimal inputlength (adjusted for the input type). The sourcecode for experimental analysis can be found atGithub.</abstract>
<identifier type="citekey">kanjirangat-etal-2022-early</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.479</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.479</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6417</start>
<end>6426</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Early Guessing for Dialect Identification
%A Kanjirangat, Vani
%A Samardzic, Tanja
%A Rinaldi, Fabio
%A Dolamic, Ljiljana
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kanjirangat-etal-2022-early
%X This paper deals with the problem of incre-mental dialect identification. Our goal is toreliably determine the dialect before the fullutterance is given as input. The major partof the previous research on dialect identification has been model-centric, focusing on performance. We address a new question: How much input is needed to identify a dialect? Ourapproach is a data-centric analysis that resultsin general criteria for finding the shortest inputneeded to make a plausible guess. Workingwith three sets of language dialects (Swiss German, Indo-Aryan and Arabic languages), weshow that it is possible to generalize across dialects and datasets with two input shorteningcriteria: model confidence and minimal inputlength (adjusted for the input type). The sourcecode for experimental analysis can be found atGithub.
%R 10.18653/v1/2022.findings-emnlp.479
%U https://aclanthology.org/2022.findings-emnlp.479
%U https://doi.org/10.18653/v1/2022.findings-emnlp.479
%P 6417-6426
Markdown (Informal)
[Early Guessing for Dialect Identification](https://aclanthology.org/2022.findings-emnlp.479) (Kanjirangat et al., Findings 2022)
ACL
- Vani Kanjirangat, Tanja Samardzic, Fabio Rinaldi, and Ljiljana Dolamic. 2022. Early Guessing for Dialect Identification. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6417–6426, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.