UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation
This work addresses semantic textual relatedness for low-resource languages, but it is incremental as it builds on existing LLM methods with mixed results across languages.
The paper tackled semantic textual relatedness for 14 African and Asian languages by developing two models, TranSem and FineSem, for supervised and cross-lingual settings, achieving better performance than the baseline for 3 languages in each setting, including 1st place for Afrikaans and 2nd for Indonesian in cross-lingual.
The aim of SemEval-2024 Task 1, "Semantic Textual Relatedness for African and Asian Languages" is to develop models for identifying semantic textual relatedness (STR) between two sentences using multiple languages (14 African and Asian languages) and settings (supervised, unsupervised, and cross-lingual). Large language models (LLMs) have shown impressive performance on several natural language understanding tasks such as multilingual machine translation (MMT), semantic similarity (STS), and encoding sentence embeddings. Using a combination of LLMs that perform well on these tasks, we developed two STR models, $\textit{TranSem}$ and $\textit{FineSem}$, for the supervised and cross-lingual settings. We explore the effectiveness of several training methods and the usefulness of machine translation. We find that direct fine-tuning on the task is comparable to using sentence embeddings and translating to English leads to better performance for some languages. In the supervised setting, our model performance is better than the official baseline for 3 languages with the remaining 4 performing on par. In the cross-lingual setting, our model performance is better than the baseline for 3 languages (leading to $1^{st}$ place for Africaans and $2^{nd}$ place for Indonesian), is on par for 2 languages and performs poorly on the remaining 7 languages. Our code is publicly available at https://github.com/dipta007/SemEval24-Task8.