MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification

Varun Vashisht; Samar Singh; Mihir Konduskar; Jaskaran Singh Walia; Vukosi Marivate

MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification

Computation and Language 2025-02-26 v1 Artificial Intelligence Information Retrieval Machine Learning

Authors: Varun Vashisht , Samar Singh , Mihir Konduskar , Jaskaran Singh Walia , Vukosi Marivate

Abstract

Due to the lack of quality data for low-resource Bantu languages, significant challenges are presented in text classification and other practical implementations. In this paper, we introduce an advanced model combining Language-Independent Data Augmentation (LiDA) with Multi-Head Attention based weighted embeddings to selectively enhance critical data points and improve text classification performance. This integration allows us to create robust data augmentation strategies that are effective across various linguistic contexts, ensuring that our model can handle the unique syntactic and semantic features of Bantu languages. This approach not only addresses the data scarcity issue but also sets a foundation for future research in low-resource language processing and classification tasks.

Keywords

sequence alignment machine translation information retrieval

Cite

@article{arxiv.2502.17987,
  title  = {MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification},
  author = {Varun Vashisht and Samar Singh and Mihir Konduskar and Jaskaran Singh Walia and Vukosi Marivate},
  journal= {arXiv preprint arXiv:2502.17987},
  year   = {2025}
}

MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification

Abstract

Keywords

Cite

Related papers