Query Matching Evaluation in an Infobot for University Admissions Processing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

Colleges, School and Institutes

Abstract

"Infobots" are small-scale natural language question answering systems drawing inspiration from ELIZA-type systems. Their key distinguishing feature is the extraction of meaning from users' queries without the use of syntactic or semantic representations. Two approaches to identifying the users' intended meanings were investigated: keyword-based systems and Jaro-based string similarity algorithms. These were measured against a corpus of queries contributed by users of a WWW-hosted infobot for responding to questions about applications to MSc courses. The most effective system was Jaro with stemmed input (78.57%). It also was able to process ungrammatical input and offer scalability.

Details

Original languageEnglish
Title of host publicationSLATE 2012
Subtitle of host publication1st Symposium on Languages, Applications and Technologies, Universidade do Minho, Braga, 21-22 June 2012
EditorsAlberto Simoes , Ricardo Queiros, Daniela da Cruz
Publication statusPublished - 21 Jun 2012
Event1st Symposium on Languages, Applications and Technologies - Braga, Portugal
Duration: 21 Jun 201222 Jun 2012

Publication series

NameOpenAccess Series in Informatics (OASIcs)
Number21
ISSN (Electronic)2190-6807

Conference

Conference1st Symposium on Languages, Applications and Technologies
CountryPortugal
CityBraga
Period21/06/1222/06/12

Keywords

  • chatbot, infobot, question-answering, Jaro string similarity, Jaro-Winkler string similarity