Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
Chiyu Song, Hongliang He, Haofei Yu, Pengfei Fang, Leyang Cui, Zhenzhong Lan
Abstract
Sample-and-rank is a key decoding strategy for modern generation-based dialogue systems. It helps achieve diverse and high-quality responses by selecting an answer from a small pool of generated candidates. The current state-of-the-art ranking methods mainly use an encoding paradigm called Cross-Encoder, which separately encodes each context-candidate pair and ranks the candidates according to their fitness scores. However, Cross-Encoder repeatedly encodes the same lengthy context for each candidate, resulting in high computational costs. Poly-Encoder addresses the above problems by reducing the interaction between context and candidates, but with a price of performance drop. In this work, we develop a new paradigm called Uni-Encoder, that keeps the full attention over each pair as in Cross-Encoder while only encoding the context once, as in Poly-Encoder. Uni-Encoder encodes all the candidates with the context in one forward pass. We use the same positional embedding for all candidates to ensure they are treated equally and design a new attention mechanism to avoid confusion. Our Uni-Encoder can simulate other ranking paradigms using different attention and response concatenation methods. Extensive experiments show that our proposed paradigm achieves new state-of-the-art results on four benchmark datasets with high computational efficiency. For instance, it improves R10@1 by 2.9% with an approximately 4X faster inference speed on the Ubuntu V2 dataset.- Anthology ID:
- 2023.findings-acl.388
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6231–6244
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.388
- DOI:
- Cite (ACL):
- Chiyu Song, Hongliang He, Haofei Yu, Pengfei Fang, Leyang Cui, and Zhenzhong Lan. 2023. Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6231–6244, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems (Song et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.findings-acl.388.pdf