Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever

09/15/2019
by   Libo Qin, et al.
0

Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system. Previous sequence-to-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities.In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/15/2021

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

End-to-End task-oriented dialogue systems generate responses based on di...
research
05/17/2023

Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog

Retrieving proper domain knowledge from an external database lies at the...
research
06/12/2018

Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation

Classic pipeline models for task-oriented dialogue system require explic...
research
09/19/2022

Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

Task-oriented dialog (TOD) systems often require interaction with an ext...
research
05/03/2018

Hierarchical Pointer Memory Network for Task Oriented Dialogue

We observe that end-to-end memory networks (MN) trained for task-oriente...
research
09/11/2019

Self-Attentional Models Application in Task-Oriented Dialogue Generation Systems

Self-attentional models are a new paradigm for sequence modelling tasks ...
research
05/15/2017

Key-Value Retrieval Networks for Task-Oriented Dialogue

Neural task-oriented dialogue systems often struggle to smoothly interfa...

Please sign up or login with your details

Forgot password? Click here to reset