Query Matching Evaluation in an Infobot for University Admissions Processing

Authors Peter Hancox, Nikolaos Polatidis



PDF
Thumbnail PDF

File

OASIcs.SLATE.2012.149.pdf
  • Filesize: 470 kB
  • 14 pages

Document Identifiers

Author Details

Peter Hancox
Nikolaos Polatidis

Cite AsGet BibTex

Peter Hancox and Nikolaos Polatidis. Query Matching Evaluation in an Infobot for University Admissions Processing. In 1st Symposium on Languages, Applications and Technologies. Open Access Series in Informatics (OASIcs), Volume 21, pp. 149-161, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2012)
https://doi.org/10.4230/OASIcs.SLATE.2012.149

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.
Keywords
  • chatbot
  • infobot
  • question-answering
  • Jaro string similarity
  • Jaro-Winkler string similarity

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail