Zhang, Miaoran; Mingyang, Wang; Jesujoba , Alabi; Klakow, Dietrich
AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness
Kr. Ojha, Atul; Seza Doğruöz, A.; Tayyar Madabushi, Harish; Da San Martino, Giovanni; Rosenthal, Sara; Rosá, Aiala (Ed.): Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), Association for Computational Linguistics, pp. 800-810, Mexico City, Mexico, 2024.
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages. The shared task aims at measuring the semantic textual relatedness between pairs of sentences, with a focus on a range of under-represented languages. In this work, we propose using machine translation for data augmentation to address the low-resource challenge of limited training data. Moreover, we apply task-adaptive pre-training on unlabeled task data to bridge the gap between pre-training and task adaptation. For model training, we investigate both full fine-tuning and adapter-based tuning, and adopt the adapter framework for effective zero-shot cross-lingual transfer. We achieve competitive results in the shared task: our system performs the best among all ranked teams in both subtask A (supervised learning) and subtask C (cross-lingual transfer).