SubmissionNumber#=%=#132 FinalPaperTitle#=%=#USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task ShortPaperTitle#=%=# NumberOfPages#=%=#7 CopyrightSigned#=%=#Jianjian Li, Shengwei Liang, Yong Liao, Hongping Deng and Haiyang Yu JobTitle#==# Organization#==# 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. Author{1}{Firstname}#=%=#Jianjian Author{1}{Lastname}#=%=#Li Author{1}{Username}#=%=#ustcljj Author{1}{Email}#=%=#sa22221088@mail.ustc.edu.cn Author{1}{Affiliation}#=%=#University of Science and Technology of China Author{2}{Firstname}#=%=#Shengwei Author{2}{Lastname}#=%=#Liang Author{2}{Username}#=%=#sewell961 Author{2}{Email}#=%=#1358411512@qq.com Author{2}{Affiliation}#=%=#University of Science and Technology of China Author{3}{Firstname}#=%=#Yong Author{3}{Lastname}#=%=#Liao Author{3}{Email}#=%=#yliao@ustc.edu.cn Author{3}{Affiliation}#=%=#University of Science and Technology of China Author{4}{Firstname}#=%=#Hongping Author{4}{Lastname}#=%=#Deng Author{4}{Email}#=%=#denghp83@gmail.com Author{4}{Affiliation}#=%=#Institute of Dataspace Author{5}{Firstname}#=%=#Haiyang Author{5}{Lastname}#=%=#Yu Author{5}{Username}#=%=#yuys0602 Author{5}{Email}#=%=#yuys0602@163.com Author{5}{Affiliation}#=%=#Zhejiang University ========== èéáğö