Semantic Text Relatedness (STR), a measure of meaning similarity between text elements, has become a key focus in the field of Natural Language Processing (NLP). We describe SemEval-2024 task 1 on Semantic Textual Relatedness featuring three tracks: supervised learning, unsupervised learning and cross-lingual learning across African and Asian languages including Afrikaans, Algerian Arabic, Amharic, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. Our goal is to analyse the semantic representation of sentences textual relatedness trained on mBert, all-MiniLM-L6-v2 and Bert-Based-uncased. The effectiveness of these models is evaluated using the Spearman Correlation metric, which assesses the strength of the relationship between paired data. The finding reveals the viability of transformer models in multilingual STR tasks.

This paper presents the work of our team, “ArewaNLP,” for the WMT 2024 shared task. The paper describes the system submitted to the Ninth Conference on Machine Translation (WMT24). We participated in the English-Hausa text-only translation task. We fine-tuned the OPUS-MT-en-ha transformer model and our submission achieved competitive results in this task. We achieve a BLUE score of 27.76, 40.31 and 5.85 on the Development Test, Evaluation Test and Challenge Test respectively.