Conversational Semantic Parsing for Dialog State Tracking

10/24/2020
by   Jianpeng Cheng, et al.
0

We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of 27k conversations annotated with tree-structured dialog states and system acts. We describe an encoder-decoder framework for DST with hierarchical representations, which leads to 20 state-of-the-art DST approaches that operate on a flat meaning space of slot-value pairs.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/09/2017

Tracking of enriched dialog states for flexible conversational information access

Dialog state tracking (DST) is a crucial component in a task-oriented di...
10/18/2018

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

Task oriented dialog systems typically first parse user utterances to se...
02/15/2019

Improving Semantic Parsing for Task Oriented Dialog

Semantic parsing using hierarchical representations has recently been pr...
09/28/2020

Conversational Semantic Parsing

The structured representation for semantic parsing in task-oriented assi...
02/20/2017

The Dialog State Tracking Challenge with Bayesian Approach

Generative model has been one of the most common approaches for solving ...
02/07/2020

MA-DST: Multi-Attention Based Scalable Dialog State Tracking

Task oriented dialog agents provide a natural language interface for use...
06/26/2017

Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability

Generative encoder-decoder models offer great promise in developing doma...