Point or Generate Dialogue State Tracker
arXiv:2008.03417
Abstract
Dialogue state tracking is a key part of a task-oriented dialogue system, which estimates the user's goal at each turn of the dialogue. In this paper, we propose the Point-Or-Generate Dialogue State Tracker (POGD). POGD solves the dialogue state tracking task in two perspectives: 1) point out explicitly expressed slot values from the user's utterance, and 2) generate implicitly expressed ones based on slot-specific contexts. It also shares parameters across all slots, which achieves knowledge sharing and gains scalability to large-scale across-domain dialogues. Moreover, the training process of its submodules is formulated as a multi-task learning procedure to further promote its capability of generalization. Experiments show that POGD not only obtains state-of-the-art results on both WoZ 2.0 and MultiWoZ 2.0 datasets but also has good generalization on unseen values and new slots.
arXiv commentrejected in emnlp-ijcnlp 2019
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- Get To The Point: Summarization with Pointer-Generator Networks
- From Paraphrase Database to Compositional Paraphrase Model and Back
- Toward Scalable Neural Dialogue State Tracking Model
- Towards Universal Dialogue State Tracking
- Improving Dialogue State Tracking by Discerning the Relevant Context