Experience-based Causality Learning for Intelligent Agents

Experience-based Causality Learning for Intelligent Agents
复制标题

智能代理基于经验的因果关系学习

DOI:
10.1145/3314943
复制
发表时间:
2019-05
期刊:
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)
影响因子:
--
通讯作者:
Chengqing Zong
Chengqing Zong
中科院分区:
其他
文献类型:
--
作者:
Yang Liu;Shaonan Wang;Jiajun Zhang;Chengqing Zong

文献摘要

参考文献

相似文献

理解文本中的因果关系对智能代理至关重要。在本文中,受人类因果关系学习的启发,我们提出了一个基于经验的因果关系学习框架。与传统的依赖文本线索和语言资源来处理因果关系问题的方法相比,我们首次将经验信息用于因果关系学习。具体来说,我们首先为智能代理构建各种场景,这样智能代理就可以从这些场景中的交互中获得经验。然后,人类参与者基于这些场景为因果关系学习代理构建许多训练实例。每个实例包含两个句子和一个标签。每个句子描述一个智能体在一个场景中经历的一个事件,标签表明句子(事件)对是否有因果关系。因此,我们提出了一种基于输入的句子对,通过访问相应的事件信息,利用经验来推断文本因果关系的模型。实验结果表明,该方法在基于因果关系的语料库上取得了令人印象深刻的效果,显著优于传统的方法。我们的研究表明,经验对于智能主体理解因果关系非常重要。
Understanding causality in text is crucial for intelligent agents. In this article, inspired by human causality learning, we propose an experience-based causality learning framework. Comparing to traditional approaches, which attempt to handle the causality problem relying on textual clues and linguistic resources, we are the first to use experience information for causality learning. Specifically, we first construct various scenarios for intelligent agents, thus, the agents can gain experience from interaction in these scenarios. Then, human participants build a number of training instances for agents of causality learning based on these scenarios. Each instance contains two sentences and a label. Each sentence describes an event that an agent experienced in a scenario, and the label indicates whether the sentence (event) pair has a causal relation. Accordingly, we propose a model that can infer the causality in text using experience by accessing the corresponding event information based on the input sentence pair. Experiment results show that our method can achieve impressive performance on the grounded causality corpus and significantly outperform the conventional approaches. Our work suggests that experience is very important for intelligent agents to understand causality.
DOI: 10.1109/cvprw.2018.00279
发表时间: 2018-06
期刊: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
Abhishek Das;Samyak Datta;Georgia Gkioxari;Stefan Lee;Devi Parikh;Dhruv Batra
通讯作者: Abhishek Das;Samyak Datta;Georgia Gkioxari;Stefan Lee;Devi Parikh;Dhruv Batra
DOI: --
发表时间: 2011-07
期刊: --
影响因子: --
作者:
Q. Do;Yee Seng Chan;D. Roth
通讯作者: Q. Do;Yee Seng Chan;D. Roth
DOI: 10.3115/1699510.1699555
发表时间: 2009-08
期刊: --
影响因子: --
作者:
Ziheng Lin;Min-Yen Kan;H. Ng
通讯作者: Ziheng Lin;Min-Yen Kan;H. Ng
DOI: 10.4324/9780203000502
发表时间: 2008-01
期刊: --
影响因子: --
作者:
Martin V. Curd;S. Psillos
通讯作者: Martin V. Curd;S. Psillos
DOI: --
发表时间: 2016-11
期刊: ArXiv
影响因子: --
作者:
Angeliki Lazaridou;A. Peysakhovich;Marco Baroni
通讯作者: Angeliki Lazaridou;A. Peysakhovich;Marco Baroni