Goal-Embedded Dual Hierarchical Model for Task-Oriented Dialogue Generation
This work addresses the challenge of improving task-oriented dialogue systems for applications like customer service or virtual assistants, though it appears incremental by building on existing hierarchical neural network approaches.
The authors tackled the problem of generating goal-oriented dialogues by proposing a model that incorporates goals and interlocutor disparities, resulting in higher-quality, more diverse, and goal-centric dialogues as demonstrated through experiments and human evaluations.
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.