Knowledge representation for context and sentiment analysis

Ireti Fakinlede, Vive Kumar, Dunwei Wen

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

1 Citation (Scopus)

Abstract

This paper presents a knowledge representation framework for natural language understanding. Here we propose an automated knowledge acquisition mechanism that mirrors information extraction in human-human interaction. This framework utilizes knowledge based automatic role labeling and automatic concept learning together with a conceptual structure that captures intent and context. The resulting framework is to be used to improve the agent's ability to engage in social interaction with humans.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE 13th International Conference on Advanced Learning Technologies, ICALT 2013
Pages493-494
Number of pages2
DOIs
Publication statusPublished - 2013
Event2013 IEEE 13th International Conference on Advanced Learning Technologies, ICALT 2013 - Beijing, China
Duration: 15 Jul. 201318 Jul. 2013

Publication series

NameProceedings - 2013 IEEE 13th International Conference on Advanced Learning Technologies, ICALT 2013

Conference

Conference2013 IEEE 13th International Conference on Advanced Learning Technologies, ICALT 2013
Country/TerritoryChina
CityBeijing
Period15/07/1318/07/13

Keywords

  • anthropomorphic agents
  • knowledge representation
  • natural language processing
  • semantic roles
  • sentiment analysis
  • social context

Fingerprint

Dive into the research topics of 'Knowledge representation for context and sentiment analysis'. Together they form a unique fingerprint.

Cite this