Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT

ACL ARR 2025 May Submission4340 Authors

Abstract: In this paper, we address the persistent challenges that figurative language expressions pose for natural language processing (NLP) systems, particularly in low-resource languages such as Konkani. We present a hybrid model that integrates a pre-trained Multilingual BERT (mBERT) with a bidirectional LSTM and a linear classifier. This architecture is fine-tuned on a newly introduced annotated dataset for metaphor classification, developed as part of this work. To improve the model’s efficiency, we implement a gradient-based attention head pruning strategy. For metaphor classification, the pruned model achieves an accuracy of 78%. We also applied our pruning approach to expand on an existing idiom classification task, achieving 83% accuracy. These results demonstrate the effectiveness of attention head pruning for building efficient NLP tools in underrepresented languages.

Paper Type: Short

Research Area: Efficient/Low-Resource Methods for NLP

Research Area Keywords: Konkani, Low-Resource Languages, Figurative Language, Metaphor Classification, Idiom Classification, Attention Head Pruning, mBERT, Transformer Efficiency

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency, Data resources

Languages Studied: Konkani

Submission Number: 4340