Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Sashank Santhanam, Zhuo Cheng, Brodie Mather, Bonnie Dorr, Archna Bhatia, Bryanna Hebenstreit, Alan Zemel, Adam Dalton, Tomek Strzalkowski, Samira Shaikh
Abstract
Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach.- Anthology ID:
- 2020.findings-emnlp.247
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2736–2750
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.247
- DOI:
- 10.18653/v1/2020.findings-emnlp.247
- Cite (ACL):
- Sashank Santhanam, Zhuo Cheng, Brodie Mather, Bonnie Dorr, Archna Bhatia, Bryanna Hebenstreit, Alan Zemel, Adam Dalton, Tomek Strzalkowski, and Samira Shaikh. 2020. Learning to Plan and Realize Separately for Open-Ended Dialogue Systems. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2736–2750, Online. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Plan and Realize Separately for Open-Ended Dialogue Systems (Santhanam et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.findings-emnlp.247.pdf