An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
arXiv:1805.01555
Abstract
We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values. Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values, especially when the spoken language understanding (SLU) module is absent as in many end-to-end (E2E) systems. We describe in this paper an E2E architecture based on the pointer network (PtrNet) that can effectively extract unknown slot values while still obtains state-of-the-art accuracy on the standard DSTC2 benchmark. We also provide extensive empirical evidence to show that tracking unknown values can be challenging and our approach can bring significant improvement with the help of an effective feature dropout technique.
arXiv commentAccepted by ACL 2018
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Improving neural networks by preventing co-adaptation of feature detectors
- Machine Comprehension Using Match-LSTM and Answer Pointer
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Pointing the Unknown Words
- End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
Cited by in corpus (6)
- Recent Advances and Challenges in Task-oriented Dialog System
- Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker
- Towards Universal Dialogue State Tracking
- DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
- ShopTalk: A System for Conversational Faceted Search
- Leveraging External Knowledge for Out-Of-Vocabulary Entity Labeling