Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures
Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, Dawei Yin
Abstract
Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces architectural complexity and fragility. We propose a novel, holistic, extendable framework based on a single sequence-to-sequence (seq2seq) model which can be optimized with supervised or reinforcement learning. A key contribution is that we design text spans named belief spans to track dialogue believes, allowing task-oriented dialogue systems to be modeled in a seq2seq way. Based on this, we propose a simplistic Two Stage CopyNet instantiation which emonstrates good scalability: significantly reducing model complexity in terms of number of parameters and training time by a magnitude. It significantly outperforms state-of-the-art pipeline-based methods on large datasets and retains a satisfactory entity match rate on out-of-vocabulary (OOV) cases where pipeline-designed competitors totally fail.- Anthology ID:
- P18-1133
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1437–1447
- Language:
- URL:
- https://aclanthology.org/P18-1133
- DOI:
- 10.18653/v1/P18-1133
- Cite (ACL):
- Wenqiang Lei, Xisen Jin, Min-Yen Kan, Zhaochun Ren, Xiangnan He, and Dawei Yin. 2018. Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1437–1447, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures (Lei et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/bionlp-24-ingestion/P18-1133.pdf
- Code
- WING-NUS/sequicity