10.4230/OASICS.SLATE.2012.149
Hancox, Peter
Peter
Hancox
Polatidis, Nikolaos
Nikolaos
Polatidis
Query Matching Evaluation in an Infobot for University Admissions Processing
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
2012
Article
chatbot
infobot
question-answering
Jaro string similarity
Jaro-Winkler string similarity
Simões, Alberto
Alberto
Simões
Queirós, Ricardo
Ricardo
Queirós
da Cruz, Daniela
Daniela
da Cruz
2012
2012-06-21
2012-06-21
2012-06-21
en
urn:nbn:de:0030-drops-35206
10.4230/OASIcs.SLATE.2012
978-3-939897-40-8
2190-6807
10.4230/OASIcs.SLATE.2012
OASIcs, Volume 21, SLATE 2012
1st Symposium on Languages, Applications and Technologies
2012
21
12
149
161
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
Simões, Alberto
Alberto
Simões
Queirós, Ricardo
Ricardo
Queirós
da Cruz, Daniela
Daniela
da Cruz
2190-6807
Open Access Series in Informatics (OASIcs)
2012
21
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
14 pages
481409 bytes
application/pdf
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license
info:eu-repo/semantics/openAccess
"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.
OASIcs, Vol. 21, 1st Symposium on Languages, Applications and Technologies, pages 149-161