Abstract
Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT-2 (Devlin et al., 2019; Radford et al., 2019) have suggested the effectiveness of incorporating language priors in down-stream NLP tasks. However, how much pre-trained language models can help dialog response generation is still under exploration. In this paper, we propose a simple, general, and effective framework: Alternating Recurrent Dialog Model (ARDM). ARDM models each speaker separately and takes advantage of the large pre-trained language model. It requires no supervision from human annotations such as belief states or dialog acts to achieve effective conversations. ARDM outperforms or is on par with state-of-the-art methods on two popular task-oriented dialog datasets: CamRest676 and MultiWOZ. Moreover, we can generalize ARDM to more challenging, non-collaborative tasks such as persuasion. In persuasion tasks, ARDM is capable of generating human-like responses to persuade people to donate to a charity.- Anthology ID:
- 2021.eacl-main.110
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1292–1301
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.110
- DOI:
- 10.18653/v1/2021.eacl-main.110
- Cite (ACL):
- Qingyang Wu, Yichi Zhang, Yu Li, and Zhou Yu. 2021. Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1292–1301, Online. Association for Computational Linguistics.
- Cite (Informal):
- Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models (Wu et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.eacl-main.110.pdf
- Code
- budzianowski/multiwoz
- Data
- MultiWOZ