MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912244582842368 |
|---|---|
| author | Vashisht, Varun Singh, Samar Konduskar, Mihir Walia, Jaskaran Singh Marivate, Vukosi |
| author_facet | Vashisht, Varun Singh, Samar Konduskar, Mihir Walia, Jaskaran Singh Marivate, Vukosi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17987 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification Vashisht, Varun Singh, Samar Konduskar, Mihir Walia, Jaskaran Singh Marivate, Vukosi Computation and Language Artificial Intelligence Information Retrieval Machine Learning 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. |
| title | MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2502.17987 |