Implicit Perception of Differences between NLP‐Produced and Human‐Produced Language in the Mentalizing Network

Author:

Wei Zhengde12,Chen Ying1,Zhao Qian2,Zhang Pengyu2,Zhou Longxi3,Ren Jiecheng2,Piao Yi24,Qiu Bensheng5,Xie Xing6,Wang Suiping7,Liu Jia8,Zhang Daren12,Kadosh Roi Cohen9,Zhang Xiaochu1254ORCID

Affiliation:

1. Department of Psychology School of Humanities & Social Science University of Science & Technology of China Hefei Anhui 230026 China

2. Department of Radiology the First Affiliated Hospital of USTC School of Life Science Division of Life Science and Medicine University of Science & Technology of China Hefei 230027 China

3. Computational Bioscience Research Center (CBRC) King Abdullah University of Science and Technology (KAUST) Thuwal 4700 Saudi Arabia

4. Application Technology Center of Physical Therapy to Brain Disorders Institute of Advanced Technology University of Science & Technology of China Hefei 230026 China

5. Centers for Biomedical Engineering School of Information Science and Technology University of Science & Technology of China Hefei Anhui 230027 China

6. Microsoft Research Asia Beijing 100080 China

7. Philosophy and Social Science Laboratory of Reading and Development in Children and Adolescents (South China Normal University) Ministry of Education Guangzhou 510631 China

8. State Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University Beijing 100875 China

9. Faculty of Health & Medical Sciences University of Surrey 30AD04 Elizabeth Fry Building Guildford GU2 7XH UK

Abstract

AbstractNatural language processing (NLP) is central to the communication with machines and among ourselves, and NLP research field has long sought to produce human‐quality language. Identification of informative criteria for measuring NLP‐produced language quality will support development of ever‐better NLP tools. The authors hypothesize that mentalizing network neural activity may be used to distinguish NLP‐produced language from human‐produced language, even for cases where human judges cannot subjectively distinguish the language source. Using the social chatbots Google Meena in English and Microsoft XiaoIce in Chinese to generate NLP‐produced language, behavioral tests which reveal that variance of personality perceived from chatbot chats is larger than for human chats are conducted, suggesting that chatbot language usage patterns are not stable. Using an identity rating task with functional magnetic resonance imaging, neuroimaging analyses which reveal distinct patterns of brain activity in the mentalizing network including the DMPFC and rTPJ in response to chatbot versus human chats that cannot be distinguished subjectively are conducted. This study illustrates a promising empirical basis for measuring the quality of NLP‐produced language: adding a judge's implicit perception as an additional criterion.

Funder

National Natural Science Foundation of China

Publisher

Wiley

Subject

General Physics and Astronomy,General Engineering,Biochemistry, Genetics and Molecular Biology (miscellaneous),General Materials Science,General Chemical Engineering,Medicine (miscellaneous)

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3