Abstract
This paper introduces LADAM, a novel method for enhancing the performance of text classification tasks. LADAM employs attention mechanisms to exchange semantically similar words between sentences. This approach generates a greater diversity of synthetic sentences compared to simpler operations like random insertions, while maintaining the context of the original sentences. Additionally, LADAM is an easy-to-use, lightweight technique that does not require external datasets or large language models. Our experimental results across five datasets demonstrate that LADAM consistently outperforms baseline methods across diverse text classification conditions.- Anthology ID:
- 2024.findings-emnlp.752
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12866–12873
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.752
- DOI:
- 10.18653/v1/2024.findings-emnlp.752
- Cite (ACL):
- Junehyung Kim and Sungjae Hwang. 2024. All You Need is Attention: Lightweight Attention-based Data Augmentation for Text Classification. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12866–12873, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- All You Need is Attention: Lightweight Attention-based Data Augmentation for Text Classification (Kim & Hwang, Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.752.pdf