Abstract
Hierarchical neural networks are often used to model inherent structures within dialogues. For goal-oriented dialogues, these models miss a mechanism adhering to the goals and neglect the distinct conversational patterns between two interlocutors. In this work, we propose Goal-Embedded Dual Hierarchical Attentional Encoder-Decoder (G-DuHA) able to center around goals and capture interlocutor-level disparity while modeling goal-oriented dialogues. Experiments on dialogue generation, response generation, and human evaluations demonstrate that the proposed model successfully generates higher-quality, more diverse and goal-centric dialogues. Moreover, we apply data augmentation via goal-oriented dialogue generation for task-oriented dialog systems with better performance achieved.- Anthology ID:
- K19-1075
- Volume:
- Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 798–811
- Language:
- URL:
- https://aclanthology.org/K19-1075
- DOI:
- 10.18653/v1/K19-1075
- Cite (ACL):
- Yi-An Lai, Arshit Gupta, and Yi Zhang. 2019. Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 798–811, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation (Lai et al., CoNLL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/K19-1075.pdf