arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14710cs.CL
收藏

基于联合对偶学习的无监督语言理解与生成

Towards Unsupervised Language Understanding and Generation by Joint Dual Learning

National Taiwan University(台湾大学)

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

摘要:

在模块化对话系统中,自然语言理解(NLU)和自然语言生成(NLG)是两个关键的组成部分,其中自然语言理解是从给定的文本中提取语义,自然语言生成是根据输入的语义表示构造相应的自然语言句子。然而,理解与生成的二重性却鲜有人探讨。先前的工作是第一次尝试,利用NLU和NLG之间的二元性,通过双监督学习框架来提高性能。然而,以前的工作仍然学习这两个组件在监督的方式,相反,本文介绍了一个通用的学习框架,有效地利用这种双重性,提供了灵活性,将监督和无监督学习算法训练语言理解和生成模型的联合方式。基准实验表明,该方法能够提高NLU和NLG的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑