License: Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license (CC BY-NC-ND 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.SLATE.2012.149
URN: urn:nbn:de:0030-drops-35206
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2012/3520/
Go to the corresponding OASIcs Volume Portal

Hancox, Peter ; Polatidis, Nikolaos

Query Matching Evaluation in an Infobot for University Admissions Processing

pdf-format:
13.pdf (0.5 MB)

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.

BibTeX - Entry

@InProceedings{hancox_et_al:OASIcs:2012:3520,
  author =	{Peter Hancox and Nikolaos Polatidis},
  title =	{{Query Matching Evaluation in an Infobot for University Admissions Processing}},
  booktitle =	{1st Symposium on Languages, Applications and Technologies},
  pages =	{149--161},
  series =	{OpenAccess Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-40-8},
  ISSN =	{2190-6807},
  year =	{2012},
  volume =	{21},
  editor =	{Alberto Sim{\~o}es and Ricardo Queir{\'o}s and Daniela da Cruz},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2012/3520},
  URN =		{urn:nbn:de:0030-drops-35206},
  doi =		{10.4230/OASIcs.SLATE.2012.149},
  annote =	{Keywords: chatbot, infobot, question-answering, Jaro string similarity, Jaro-Winkler string similarity}
}

Keywords: chatbot, infobot, question-answering, Jaro string similarity, Jaro-Winkler string similarity
Collection: 1st Symposium on Languages, Applications and Technologies
Issue Date: 2012
Date of publication: 21.06.2012

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI