-
Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems
In task-oriented dialogue systems the dialogue state tracker (DST) compo...
read it
-
Towards Universal Dialogue State Tracking
Dialogue state tracking is the core part of a spoken dialogue system. It...
read it
-
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
Existing approaches to dialogue state tracking rely on pre-defined ontol...
read it
-
BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer
An important yet rarely tackled problem in dialogue state tracking (DST)...
read it
-
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
Natural language generation lies at the core of generative dialogue syst...
read it
-
Scalable Neural Dialogue State Tracking
A Dialogue State Tracker (DST) is a key component in a dialogue system a...
read it
-
Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
Goal-oriented dialogue systems typically rely on components specifically...
read it
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of separate triples (domain-slot-value), in this paper, we employ a structured state representation and cast dialogue state tracking as a sequence generation problem. Based on this new formulation, we propose a CoaRsE-to-fine DIalogue state Tracking (CREDIT) approach. Taking advantage of the structured state representation, which is a marked language sequence, we can further fine-tune the pre-trained model (by supervised learning) by optimizing natural language metrics with the policy gradient method. Like all generative state tracking methods, CREDIT does not rely on pre-defined dialogue ontology enumerating all possible slot values. Experiments demonstrate our tracker achieves encouraging joint goal accuracy for the five domains in MultiWOZ 2.0 and MultiWOZ 2.1 datasets.
READ FULL TEXT
Comments
There are no comments yet.