Scalable Multi-Domain Dialogue State Tracking

by   Abhinav Rastogi, et al.

Dialogue state tracking (DST) is a key component of task-oriented dialogue systems. DST estimates the user's goal at each user turn given the interaction until then. State of the art approaches for state tracking rely on deep learning methods, and represent dialogue state as a distribution over all possible slot values for each slot present in the ontology. Such a representation is not scalable when the set of possible values are unbounded (e.g., date, time or location) or dynamic (e.g., movies or usernames). Furthermore, training of such models requires labeled data, where each user turn is annotated with the dialogue state, which makes building models for new domains challenging. In this paper, we present a scalable multi-domain deep learning based approach for DST. We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge. Restricting these candidate sets to be bounded in size addresses the problem of slot-scalability. Furthermore, by leveraging the slot-independent architecture and transfer learning, we show that our proposed approach facilitates quick adaptation to new domains.


A Robust Data-Driven Approach for Dialogue State Tracking of Unseen Slot Values

A Dialogue State Tracker is a key component in dialogue systems which es...

HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking

Recent works on end-to-end trainable neural network based approaches hav...

Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering

Multi-domain dialogue state tracking (DST) is a critical component for c...

Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation

Existing approaches to dialogue state tracking rely on pre-defined ontol...

Multi-task learning for Joint Language Understanding and Dialogue State Tracking

This paper presents a novel approach for multi-task learning of language...

CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

In dialogue systems, a dialogue state tracker aims to accurately find a ...

Leveraging External Knowledge for Out-Of-Vocabulary Entity Labeling

Dealing with previously unseen slots is a challenging problem in a real-...

Please sign up or login with your details

Forgot password? Click here to reset