Abstract
Two principles: the complementary principle and the consensus principle are widely acknowledged in the literature of multi-view learning. However, the current design of multi-head self-attention, an instance of multi-view learning, prioritizes the complementarity while ignoring the consensus. To address this problem, we propose an enhanced multi-head self-attention (EMHA). First, to satisfy the complementary principle, EMHA removes the one-to-one mapping constraint among queries and keys in multiple subspaces and allows each query to attend to multiple keys. On top of that, we develop a method to fully encourage consensus among heads by introducing two interaction models, namely inner-subspace interaction and cross-subspace interaction. Extensive experiments on a wide range of language tasks (e.g., machine translation, abstractive summarization and grammar correction, language modeling), show its superiority, with a very modest increase in model size. Our code would be available at: https://github.com/zhengkid/EIT-Enhanced-Interactive-Transformer.- Anthology ID:
- 2024.acl-long.418
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7734–7751
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.418
- DOI:
- 10.18653/v1/2024.acl-long.418
- Cite (ACL):
- Tong Zheng, Bei Li, Huiwen Bao, Tong Xiao, and JingBo Zhu. 2024. EIT: Enhanced Interactive Transformer. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7734–7751, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- EIT: Enhanced Interactive Transformer (Zheng et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.acl-long.418.pdf