A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning

IJCAI, pp. 4403-4410, 2018.

Cited by: 14|Views62
EI
Weibo:
We propose a reinforcement learning method for topic segmentation and labeling in goal-oriented dialogues, which aims to detect topic boundaries among dialogue utterances and assign topic labels to the utterances

Abstract:

Topic structure analysis plays a pivotal role in dialogue understanding. We propose a reinforcement learning (RL) method for topic segmentation and labeling in goal-oriented dialogues, which aims to detect topic boundaries among dialogue utterances and assign topic labels to the utterances. We address three common issues in the goal-orien...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments