Towards Unsupervised Language Understanding and Generation by Joint Dual Learning

Shang-Yu Su, Chao-Wei Huang, Yun-Nung Chen

Abstract Paper Share

Dialogue and Interactive Systems Long Paper

Session 1B: Jul 6 (06:00-07:00 GMT)
Session 2A: Jul 6 (08:00-09:00 GMT)
Abstract: In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural language sentences based on the input semantic representations. However, the dual property between understanding and generation has been rarely explored. The prior work is the first attempt that utilized the duality between NLU and NLG to improve the performance via a dual supervised learning framework. However, the prior work still learned both components in a supervised manner; instead, this paper introduces a general learning framework to effectively exploit such duality, providing flexibility of incorporating both supervised and unsupervised learning algorithms to train language understanding and generation models in a joint fashion. The benchmark experiments demonstrate that the proposed approach is capable of boosting the performance of both NLU and NLG. The source code is available at: https://github.com/MiuLab/DuaLUG.
You can open the pre-recorded video in a separate window.
NOTE: The SlidesLive video may display a random order of the authors. The correct author list is shown at the top of this webpage.

Similar Papers

A Generative Model for Joint Natural Language Understanding and Generation
Bo-Hsiang Tseng, Jianpeng Cheng, Yimai Fang, David Vandyke,
A representative figure from paper main.163
Logical Natural Language Generation from Open-Domain Tables
Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, William Yang Wang,
A representative figure from paper main.708
Curriculum Learning for Natural Language Understanding
Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, Yongdong Zhang,
A representative figure from paper main.542
Embarrassingly Simple Unsupervised Aspect Extraction
Stéphan Tulkens, Andreas van Cranenburgh,
A representative figure from paper main.290