An approach for intention perception based on knowledge network

Huakang Li, Guozi Sun, Bei Xu

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

Abstract

Intention perception is an enormous challenge for intelligent system in a short conversation. This paper introduces an approach for intention perception based on knowledge network during human-computer interaction. The entity knowledge network is build using the incidence relation between entity and attribute words. Entity and attributed words are extracted from massive crawled topic contents. The intention of user is identified using an atlas walk algorithm based on the keywords of user input. Experiment results show that the proposed algorithm based on knowledge network precept user's intent more precisely.

Original languageEnglish
Title of host publicationProceedings - 2014 10th International Conference on Semantics, Knowledge and Grids, SKG 2014
EditorsHai Zhuge, Xiaoping Sun
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages133-136
Number of pages4
ISBN (Electronic)9781479967155
DOIs
Publication statusPublished - 20 Nov 2014
Externally publishedYes
Event10th International Conference on Semantics, Knowledge and Grids, SKG 2014 - Beijing, China
Duration: 27 Aug 201429 Aug 2014

Publication series

NameProceedings - 2014 10th International Conference on Semantics, Knowledge and Grids, SKG 2014

Conference

Conference10th International Conference on Semantics, Knowledge and Grids, SKG 2014
Country/TerritoryChina
CityBeijing
Period27/08/1429/08/14

Keywords

  • Conversation System
  • Graph Path
  • Intention Perception
  • Knowledge network
  • Web Intelligence

Fingerprint

Dive into the research topics of 'An approach for intention perception based on knowledge network'. Together they form a unique fingerprint.

Cite this