An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
Puyang Xu, Qi Hu

TL;DR
This paper presents an end-to-end dialogue state tracking method using pointer networks to effectively handle unknown slot values, improving accuracy especially when the spoken language understanding module is absent.
Contribution
Introduces a novel E2E architecture based on pointer networks for handling unknown slot values in dialogue state tracking, with effective feature dropout techniques.
Findings
Achieves state-of-the-art accuracy on DSTC2 benchmark.
Effectively extracts unknown slot values in end-to-end systems.
Feature dropout significantly improves tracking performance.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and dialogue systems · Topic Modeling · Natural Language Processing Techniques
MethodsSigmoid Activation · Tanh Activation · [LivE@PeRson]How do I talk to a real person at Expedia? · Softmax · Long Short-Term Memory · Pointer Network
