Skip to main navigation Skip to search Skip to main content

Conscious knowledge based question answering

  • Shirong Liu*
  • , Zixian Guo*
  • , Hongzhi Wang
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A model of consciousness proposed by neuroscientists in 1989 is called the theater model, which uses theater as an analogy to describe "what is consciousness". This paper simplifies the problem of question answering and uses theater model to simulate the question answering mechanism of the human brain. We extract a small amount of knowledge from Freebase and use it as agents' knowledge base. Then we build a multi-round question answering agent based on the theater model and Deep Q-learning. We train the two agents against each other, and finally analyze the training results. The results show that the question answering mechanism and training method designed can simulate the human dialogue scene well, and agents have different behavior when setting different rewarding parameters.

Original languageEnglish
Title of host publicationACM TURC 2020 - Proceedings of ACM Turing Celebration Conference - China
PublisherAssociation for Computing Machinery
Pages145-149
Number of pages5
ISBN (Electronic)9781450375344
DOIs
StatePublished - 22 May 2020
Event2020 ACM Turing Celebration Conference - China, ACM TURC 2020 - Hefei, China
Duration: 21 May 202123 May 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2020 ACM Turing Celebration Conference - China, ACM TURC 2020
Country/TerritoryChina
CityHefei
Period21/05/2123/05/21

Keywords

  • Conscious machine
  • Question answering
  • Reinforcement learning
  • Theater model of consciousness

Fingerprint

Dive into the research topics of 'Conscious knowledge based question answering'. Together they form a unique fingerprint.

Cite this