USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task
This work addresses cross-lingual communication challenges for applications like machine translation, but it is incremental as it builds on existing models and techniques.
The paper tackled the cross-lingual semantic textual relatedness task by using XLM-R-base with whitening to reduce anisotropy and a data filtering method, achieving second place in Spanish and third in Indonesian in the competition.
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.