A Semantic Layer on Semi-Structured Data Sources for Intuitive Chatbots
- 1 March 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 760-765
- https://doi.org/10.1109/cisis.2009.165
Abstract
The main limits of chatbot technology are related to the building of their knowledge representation and to their rigid information retrieval and dialogue capabilities, usually based on simple "pattern matching rules". The analysis of distributional properties of words in a texts corpus allows the creation of semantic spaces where represent and compare natural language elements. This space can be interpreted as a "conceptual" space where the axes represent the latent primitive concepts of the analyzed corpus.The presented work aims at exploiting the properties of a data-driven semantic/conceptual space built using semistructured data sources freely available on the Web, like Wikipedia. This coding is equivalent to adding, into the Wikipedia graph, a conceptual similarity relationship layer. The chatbot can exploit this layer in order to simulate an "intuitive" behavior, attempting to retrieve semantic relations between Wikipedia resources also through associative sub-symbolic paths.Keywords
This publication has 9 references indexed in Scilit:
- The Anatomy of A.L.I.C.E.Published by Springer Science and Business Media LLC ,2007
- Autonomously semantifying wikipediaPublished by Association for Computing Machinery (ACM) ,2007
- YagoPublished by Association for Computing Machinery (ACM) ,2007
- A semantic Bayesian network approach to retrieving information with intelligent conversational agentsInformation Processing & Management, 2007
- Developing a Conversational Agent Using OntologiesLecture Notes in Computer Science, 2007
- An Embodied Conversational Agent for Intelligent Web Interaction on Pandemic Crisis CommunicationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Semantic WikipediaPublished by Association for Computing Machinery (ACM) ,2006
- An introduction to latent semantic analysisDiscourse Processes, 1998
- Introduction to WordNet: An On-line Lexical Database*International Journal of Lexicography, 1990