@inproceedings{chavan-patwardhan-2023-chapat,
title = "{C}ha{P}at at {S}em{E}val-2023 Task 9: Text Intimacy Analysis using Ensembles of Multilingual Transformers",
author = "Chavan, Tanmay and
Patwardhan, Ved",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.181",
doi = "10.18653/v1/2023.semeval-1.181",
pages = "1304--1310",
abstract = "Intimacy estimation of a given text has recently gained importance due to the increase in direct interaction of NLP systems with humans. Intimacy is an important aspect of natural language and has a substantial impact on our everyday communication. Thus the level of intimacy can provide us with deeper insights and richer semantics of conversations. In this paper, we present our work on the SemEval shared task 9 on predicting the level of intimacy for the given text. The dataset consists of tweets in ten languages, out of which only six are available in the training dataset. We conduct several experiments and show that an ensemble of multilingual models along with a language-specific monolingual model has the best performance. We also evaluate other data augmentation methods such as translation and present the results. Lastly, we study the results thoroughly and present some noteworthy insights into this problem.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chavan-patwardhan-2023-chapat">
<titleInfo>
<title>ChaPat at SemEval-2023 Task 9: Text Intimacy Analysis using Ensembles of Multilingual Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanmay</namePart>
<namePart type="family">Chavan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ved</namePart>
<namePart type="family">Patwardhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Intimacy estimation of a given text has recently gained importance due to the increase in direct interaction of NLP systems with humans. Intimacy is an important aspect of natural language and has a substantial impact on our everyday communication. Thus the level of intimacy can provide us with deeper insights and richer semantics of conversations. In this paper, we present our work on the SemEval shared task 9 on predicting the level of intimacy for the given text. The dataset consists of tweets in ten languages, out of which only six are available in the training dataset. We conduct several experiments and show that an ensemble of multilingual models along with a language-specific monolingual model has the best performance. We also evaluate other data augmentation methods such as translation and present the results. Lastly, we study the results thoroughly and present some noteworthy insights into this problem.</abstract>
<identifier type="citekey">chavan-patwardhan-2023-chapat</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.181</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.181</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1304</start>
<end>1310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ChaPat at SemEval-2023 Task 9: Text Intimacy Analysis using Ensembles of Multilingual Transformers
%A Chavan, Tanmay
%A Patwardhan, Ved
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chavan-patwardhan-2023-chapat
%X Intimacy estimation of a given text has recently gained importance due to the increase in direct interaction of NLP systems with humans. Intimacy is an important aspect of natural language and has a substantial impact on our everyday communication. Thus the level of intimacy can provide us with deeper insights and richer semantics of conversations. In this paper, we present our work on the SemEval shared task 9 on predicting the level of intimacy for the given text. The dataset consists of tweets in ten languages, out of which only six are available in the training dataset. We conduct several experiments and show that an ensemble of multilingual models along with a language-specific monolingual model has the best performance. We also evaluate other data augmentation methods such as translation and present the results. Lastly, we study the results thoroughly and present some noteworthy insights into this problem.
%R 10.18653/v1/2023.semeval-1.181
%U https://aclanthology.org/2023.semeval-1.181
%U https://doi.org/10.18653/v1/2023.semeval-1.181
%P 1304-1310
Markdown (Informal)
[ChaPat at SemEval-2023 Task 9: Text Intimacy Analysis using Ensembles of Multilingual Transformers](https://aclanthology.org/2023.semeval-1.181) (Chavan & Patwardhan, SemEval 2023)
ACL