Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations

TL;DR

This paper explores fine-tuning RoBERTa transformer models for sentence-level Semantic Textual Relatedness scoring across multiple languages, showing promising results especially in Latin languages, with notable improvements over traditional methods.

Contribution

The study demonstrates the effectiveness of transformer-based regression models for multilingual STR, highlighting their advantages and limitations across different languages.

Findings

Achieved a correlation of 0.82 in English, ranking 19th.

Achieved a correlation of 0.67 in Spanish, ranking 15th.

Achieved a correlation of 0.38 in Arabic, ranking 20th.

Abstract

Semantic Textual Relatedness holds significant relevance in Natural Language Processing, finding applications across various domains. Traditionally, approaches to STR have relied on knowledge-based and statistical methods. However, with the emergence of Large Language Models, there has been a paradigm shift, ushering in new methodologies. In this paper, we delve into the investigation of sentence-level STR within Track A (Supervised) by leveraging fine-tuning techniques on the RoBERTa transformer. Our study focuses on assessing the efficacy of this approach across different languages. Notably, our findings indicate promising advancements in STR performance, particularly in Latin languages. Specifically, our results demonstrate notable improvements in English, achieving a correlation of 0.82 and securing a commendable 19th rank. Similarly, in Spanish, we achieved a correlation of 0.67, securing the 15th position. However, our approach encounters challenges in languages like Arabic, where we observed a correlation of only 0.38, resulting in a 20th rank.