Efficient Classification of Long Documents via State-Space Models

Peng Lu, Suyuchen Wang, Mehdi Rezagholizadeh, Bang Liu, Ivan Kobyzev


Abstract
Transformer-based models have achieved state-of-the-art performance on numerous NLP applications. However, long documents which are prevalent in real-world scenarios cannot be efficiently processed by transformers with the vanilla self-attention module due to their quadratic computation complexity and limited length extrapolation ability. Instead of tackling the computation difficulty for self-attention with sparse or hierarchical structures, in this paper, we investigate the use of State-Space Models (SSMs) for long document classification tasks. We conducted extensive experiments on six long document classification datasets, including binary, multi-class, and multi-label classification, comparing SSMs (with and without pre-training) to self-attention-based models. We also introduce the SSM-pooler model and demonstrate that it achieves comparable performance while being on average 36% more efficient. Additionally our method exhibits higher robustness to the input noise even in the extreme scenario of 40%.
Anthology ID:
2023.emnlp-main.404
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6559–6565
Language:
URL:
https://aclanthology.org/2023.emnlp-main.404
DOI:
10.18653/v1/2023.emnlp-main.404
Bibkey:
Cite (ACL):
Peng Lu, Suyuchen Wang, Mehdi Rezagholizadeh, Bang Liu, and Ivan Kobyzev. 2023. Efficient Classification of Long Documents via State-Space Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6559–6565, Singapore. Association for Computational Linguistics.
Cite (Informal):
Efficient Classification of Long Documents via State-Space Models (Lu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.404.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.404.mp4