@inproceedings{li-etal-2024-ustcctsu,
title = "{USTCCTSU} at {S}em{E}val-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task",
author = "Li, Jianjian and
Liang, Shengwei and
Liao, Yong and
Deng, Hongping and
Yu, Haiyang",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.126/",
doi = "10.18653/v1/2024.semeval-1.126",
pages = "881--887",
abstract = "Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding. It helps establish semantic connections between different languages, crucial for downstream tasks like machine translation, multilingual information retrieval, and cross-lingual text understanding.Based on extensive comparative experiments, we choose the XLM-R-base as our base model and use pre-trained sentence representations based on whitening to reduce anisotropy.Additionally, for the given training data, we design a delicate data filtering method to alleviate the curse of multilingualism. With our approach, we achieve a 2nd score in Spanish, a 3rd in Indonesian, and multiple entries in the top ten results in the competition`s track C. We further do a comprehensive analysis to inspire future research aimed at improving performance on cross-lingual tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-ustcctsu">
<titleInfo>
<title>USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianjian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengwei</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongping</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</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">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding. It helps establish semantic connections between different languages, crucial for downstream tasks like machine translation, multilingual information retrieval, and cross-lingual text understanding.Based on extensive comparative experiments, we choose the XLM-R-base as our base model and use pre-trained sentence representations based on whitening to reduce anisotropy.Additionally, for the given training data, we design a delicate data filtering method to alleviate the curse of multilingualism. With our approach, we achieve a 2nd score in Spanish, a 3rd in Indonesian, and multiple entries in the top ten results in the competition‘s track C. We further do a comprehensive analysis to inspire future research aimed at improving performance on cross-lingual tasks.</abstract>
<identifier type="citekey">li-etal-2024-ustcctsu</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.126</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.126/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>881</start>
<end>887</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
%A Li, Jianjian
%A Liang, Shengwei
%A Liao, Yong
%A Deng, Hongping
%A Yu, Haiyang
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F li-etal-2024-ustcctsu
%X Cross-lingual semantic textual relatedness task is an important research task that addresses challenges in cross-lingual communication and text understanding. It helps establish semantic connections between different languages, crucial for downstream tasks like machine translation, multilingual information retrieval, and cross-lingual text understanding.Based on extensive comparative experiments, we choose the XLM-R-base as our base model and use pre-trained sentence representations based on whitening to reduce anisotropy.Additionally, for the given training data, we design a delicate data filtering method to alleviate the curse of multilingualism. With our approach, we achieve a 2nd score in Spanish, a 3rd in Indonesian, and multiple entries in the top ten results in the competition‘s track C. We further do a comprehensive analysis to inspire future research aimed at improving performance on cross-lingual tasks.
%R 10.18653/v1/2024.semeval-1.126
%U https://aclanthology.org/2024.semeval-1.126/
%U https://doi.org/10.18653/v1/2024.semeval-1.126
%P 881-887
Markdown (Informal)
[USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task](https://aclanthology.org/2024.semeval-1.126/) (Li et al., SemEval 2024)
ACL