@inproceedings{zheng-2023-wku,
title = "{WKU}{\_}{NLP} at {S}em{E}val-2023 Task 9: Translation Augmented Multilingual Tweet Intimacy Analysis",
author = "Zheng, Qinyuan",
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-1.210",
doi = "10.18653/v1/2023.semeval-1.210",
pages = "1525--1530",
abstract = "This paper describes a system for the SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis. This system consists of a pretrained multilingual masked language model as a text encoder and a neural network as a regression model. Data augmentation based on neural machine translation models is adopted to improve model performance under the low-resource scenario. This system is further improved through the ensemble of multiple models with the best performance in each language. This system ranks 4th in languages unseen in the training data and 16th in languages seen in the training data. The code and data can be found in this link: \url{https://github.com/Cloudy0219/Multilingual}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-2023-wku">
<titleInfo>
<title>WKU_NLP at SemEval-2023 Task 9: Translation Augmented Multilingual Tweet Intimacy Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qinyuan</namePart>
<namePart type="family">Zheng</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>This paper describes a system for the SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis. This system consists of a pretrained multilingual masked language model as a text encoder and a neural network as a regression model. Data augmentation based on neural machine translation models is adopted to improve model performance under the low-resource scenario. This system is further improved through the ensemble of multiple models with the best performance in each language. This system ranks 4th in languages unseen in the training data and 16th in languages seen in the training data. The code and data can be found in this link: https://github.com/Cloudy0219/Multilingual.</abstract>
<identifier type="citekey">zheng-2023-wku</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.210</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.210</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1525</start>
<end>1530</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WKU_NLP at SemEval-2023 Task 9: Translation Augmented Multilingual Tweet Intimacy Analysis
%A Zheng, Qinyuan
%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 zheng-2023-wku
%X This paper describes a system for the SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis. This system consists of a pretrained multilingual masked language model as a text encoder and a neural network as a regression model. Data augmentation based on neural machine translation models is adopted to improve model performance under the low-resource scenario. This system is further improved through the ensemble of multiple models with the best performance in each language. This system ranks 4th in languages unseen in the training data and 16th in languages seen in the training data. The code and data can be found in this link: https://github.com/Cloudy0219/Multilingual.
%R 10.18653/v1/2023.semeval-1.210
%U https://aclanthology.org/2023.semeval-1.210
%U https://doi.org/10.18653/v1/2023.semeval-1.210
%P 1525-1530
Markdown (Informal)
[WKU_NLP at SemEval-2023 Task 9: Translation Augmented Multilingual Tweet Intimacy Analysis](https://aclanthology.org/2023.semeval-1.210) (Zheng, SemEval 2023)
ACL