DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning

11/11/2019
by   Zhuoxuan Jiang, et al.
0

In end-to-end dialogue modeling and agent learning, it is important to (1) effectively learn knowledge from data, and (2) fully utilize heterogeneous information, e.g., dialogue act flow and utterances. However, the majority of existing methods cannot simultaneously satisfy the two conditions. For example, rule definition and data labeling during system design take too much manual work, and sequence-to-sequence methods only model one-side utterance information. In this paper, we propose a novel joint end-to-end model by multi-task representation learning, which can capture the knowledge from heterogeneous information through automatically learning knowledgeable low-dimensional embeddings from data, named with DialogAct2Vec. The model requires little manual work for intervention in system design and we find that the multi-task learning can greatly improve the effectiveness of representation learning. Extensive experiments on a public dataset for restaurant reservation show that the proposed method leads to significant improvements against the state-of-the-art baselines on both the act prediction task and utterance prediction task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2019

GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue

Ellipsis and co-reference are common and ubiquitous especially in multi-...
research
08/15/2019

Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability

Learning an efficient manager of dialogue agent from data with little ma...
research
11/22/2021

Hierarchical Knowledge Distillation for Dialogue Sequence Labeling

This paper presents a novel knowledge distillation method for dialogue s...
research
04/04/2019

Dialogue Act Classification with Context-Aware Self-Attention

Recent work in Dialogue Act classification has treated the task as a seq...
research
01/10/2022

Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach

Graph Neural Networks (GNNs) have become the state-of-the-art method for...
research
05/26/2023

Adversarial Multi-task Learning for End-to-end Metaphor Detection

Metaphor detection (MD) suffers from limited training data. In this pape...
research
05/27/2019

MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network

Recently, the Network Representation Learning (NRL) techniques, which re...

Please sign up or login with your details

Forgot password? Click here to reset