CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Experience-based Causality Learning for Intelligent Agents
Yang Liu1; Shaonan Wang1; Jiajun Zhang1; Chengqing Zong2
Source PublicationAsian and Low-Resource Language Information Processing (TALLIP)
2019
Volume18Issue:4Pages:1-22
Subtype基础类研究
Abstract

Understanding causality in text is crucial for intelligent agents. In this paper, inspired by human causality learning, we propose an experience-based causality learning framework. Comparing to traditional approaches which attempt to handle 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 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 which 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 the experience is very important for intelligent agents to understand causality.
 

KeywordIntelligent Agent, Causality Learning, Grounded Language Learning, Experience, Virtual Environment
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23995
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorYang Liu
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, University of Chinese Academy of Sciences
2.National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, University of Chinese Academy of Sciences, CAS Center for Excellence in Brain Science and Intelligence Technology
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yang Liu,Shaonan Wang,Jiajun Zhang,et al. Experience-based Causality Learning for Intelligent Agents[J]. Asian and Low-Resource Language Information Processing (TALLIP),2019,18(4):1-22.
APA Yang Liu,Shaonan Wang,Jiajun Zhang,&Chengqing Zong.(2019).Experience-based Causality Learning for Intelligent Agents.Asian and Low-Resource Language Information Processing (TALLIP),18(4),1-22.
MLA Yang Liu,et al."Experience-based Causality Learning for Intelligent Agents".Asian and Low-Resource Language Information Processing (TALLIP) 18.4(2019):1-22.
Files in This Item: Download All
File Name/Size DocType Version Access License
a45-liu.pdf(3378KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang Liu]'s Articles
[Shaonan Wang]'s Articles
[Jiajun Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang Liu]'s Articles
[Shaonan Wang]'s Articles
[Jiajun Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang Liu]'s Articles
[Shaonan Wang]'s Articles
[Jiajun Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: a45-liu.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.