@inproceedings{s-etal-2022-tamilatis,
title = "{T}amil{ATIS}: Dataset for Task-Oriented Dialog in {T}amil",
author = "S, Ramaneswaran and
Vijay, Sanchit and
Srinivasan, Kathiravan",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.4/",
doi = "10.18653/v1/2022.dravidianlangtech-1.4",
pages = "25--32",
abstract = "Task-Oriented Dialogue (TOD) systems allow users to accomplish tasks by giving directions to the system using natural language utterances. With the widespread adoption of conversational agents and chat platforms, TOD has become mainstream in NLP research today. However, developing TOD systems require massive amounts of data, and there has been limited work done for TOD in low-resource languages like Tamil. Towards this objective, we introduce TamilATIS - a TOD dataset for Tamil which contains 4874 utterances. We present a detailed account of the entire data collection and data annotation process. We train state-of-the-art NLU models and report their performances. The joint BERT model with XLM-Roberta as utterance encoder achieved the highest score with an intent accuracy of 96.26{\%} and slot F1 of 94.01{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-etal-2022-tamilatis">
<titleInfo>
<title>TamilATIS: Dataset for Task-Oriented Dialog in Tamil</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramaneswaran</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanchit</namePart>
<namePart type="family">Vijay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathiravan</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sinnathamby</namePart>
<namePart type="family">Mahesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Task-Oriented Dialogue (TOD) systems allow users to accomplish tasks by giving directions to the system using natural language utterances. With the widespread adoption of conversational agents and chat platforms, TOD has become mainstream in NLP research today. However, developing TOD systems require massive amounts of data, and there has been limited work done for TOD in low-resource languages like Tamil. Towards this objective, we introduce TamilATIS - a TOD dataset for Tamil which contains 4874 utterances. We present a detailed account of the entire data collection and data annotation process. We train state-of-the-art NLU models and report their performances. The joint BERT model with XLM-Roberta as utterance encoder achieved the highest score with an intent accuracy of 96.26% and slot F1 of 94.01%.</abstract>
<identifier type="citekey">s-etal-2022-tamilatis</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.4/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>25</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TamilATIS: Dataset for Task-Oriented Dialog in Tamil
%A S, Ramaneswaran
%A Vijay, Sanchit
%A Srinivasan, Kathiravan
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F s-etal-2022-tamilatis
%X Task-Oriented Dialogue (TOD) systems allow users to accomplish tasks by giving directions to the system using natural language utterances. With the widespread adoption of conversational agents and chat platforms, TOD has become mainstream in NLP research today. However, developing TOD systems require massive amounts of data, and there has been limited work done for TOD in low-resource languages like Tamil. Towards this objective, we introduce TamilATIS - a TOD dataset for Tamil which contains 4874 utterances. We present a detailed account of the entire data collection and data annotation process. We train state-of-the-art NLU models and report their performances. The joint BERT model with XLM-Roberta as utterance encoder achieved the highest score with an intent accuracy of 96.26% and slot F1 of 94.01%.
%R 10.18653/v1/2022.dravidianlangtech-1.4
%U https://aclanthology.org/2022.dravidianlangtech-1.4/
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.4
%P 25-32
Markdown (Informal)
[TamilATIS: Dataset for Task-Oriented Dialog in Tamil](https://aclanthology.org/2022.dravidianlangtech-1.4/) (S et al., DravidianLangTech 2022)
ACL
- Ramaneswaran S, Sanchit Vijay, and Kathiravan Srinivasan. 2022. TamilATIS: Dataset for Task-Oriented Dialog in Tamil. In Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages, pages 25–32, Dublin, Ireland. Association for Computational Linguistics.