@inproceedings{suri-etal-2023-wader,
title = "{WADER} at {S}em{E}val-2023 Task 9: A Weak-labelling framework for Data augmentation in t{E}xt Regression Tasks",
author = "Suri, Manan and
Garg, Aaryak and
Chaudhary, Divya and
Gorton, Ian and
Kumar, Bijendra",
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-1.267",
doi = "10.18653/v1/2023.semeval-1.267",
pages = "1945--1952",
abstract = "Intimacy is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as a benchmark for testing computational models{'} ability to understand social information. In this paper, we propose a novel weak-labeling strategy for data augmentation in text regression tasks called WADER. WADER uses data augmentation to address the problems of data imbalance and data scarcity and provides a method for data augmentation in cross-lingual, zero-shot tasks. We benchmark the performance of State-of-the-Art pre-trained multilingual language models using WADER and analyze the use of sampling techniques to mitigate bias in data and optimally select augmentation candidates. Our results show that WADER outperforms the baseline model and provides a direction for mitigating data imbalance and scarcity in text regression tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suri-etal-2023-wader">
<titleInfo>
<title>WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manan</namePart>
<namePart type="family">Suri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaryak</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Divya</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Gorton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bijendra</namePart>
<namePart type="family">Kumar</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 is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as a benchmark for testing computational models’ ability to understand social information. In this paper, we propose a novel weak-labeling strategy for data augmentation in text regression tasks called WADER. WADER uses data augmentation to address the problems of data imbalance and data scarcity and provides a method for data augmentation in cross-lingual, zero-shot tasks. We benchmark the performance of State-of-the-Art pre-trained multilingual language models using WADER and analyze the use of sampling techniques to mitigate bias in data and optimally select augmentation candidates. Our results show that WADER outperforms the baseline model and provides a direction for mitigating data imbalance and scarcity in text regression tasks.</abstract>
<identifier type="citekey">suri-etal-2023-wader</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.267</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.267</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1945</start>
<end>1952</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks
%A Suri, Manan
%A Garg, Aaryak
%A Chaudhary, Divya
%A Gorton, Ian
%A Kumar, Bijendra
%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 suri-etal-2023-wader
%X Intimacy is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as a benchmark for testing computational models’ ability to understand social information. In this paper, we propose a novel weak-labeling strategy for data augmentation in text regression tasks called WADER. WADER uses data augmentation to address the problems of data imbalance and data scarcity and provides a method for data augmentation in cross-lingual, zero-shot tasks. We benchmark the performance of State-of-the-Art pre-trained multilingual language models using WADER and analyze the use of sampling techniques to mitigate bias in data and optimally select augmentation candidates. Our results show that WADER outperforms the baseline model and provides a direction for mitigating data imbalance and scarcity in text regression tasks.
%R 10.18653/v1/2023.semeval-1.267
%U https://aclanthology.org/2023.semeval-1.267
%U https://doi.org/10.18653/v1/2023.semeval-1.267
%P 1945-1952
Markdown (Informal)
[WADER at SemEval-2023 Task 9: A Weak-labelling framework for Data augmentation in tExt Regression Tasks](https://aclanthology.org/2023.semeval-1.267) (Suri et al., SemEval 2023)
ACL