Geodesic
An evaluation of keyword, string similarity and very shallow syntactic matching for a university admissions processing infobot
Computer Science and Information Systems, Tome 10 (2013) no. 4.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

“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. Three approaches to identifying the users’ intended meanings were investigated: keywordbased systems, Jaro-based string similarity algorithms and matching based on very shallow syntactic analysis. 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, shallow syntactic processing 
@article{CSIS_2013_10_4_a10,
     author = {Peter Hancox and Nikolaos Polatidis},
     title = {An evaluation of keyword, string similarity and very shallow syntactic matching for a university admissions processing infobot},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {10},
     number = {4},
     year = {2013},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2013_10_4_a10/}
}
TY  - JOUR
AU  - Peter Hancox
AU  - Nikolaos Polatidis
TI  - An evaluation of keyword, string similarity and very shallow syntactic matching for a university admissions processing infobot
JO  - Computer Science and Information Systems
PY  - 2013
VL  - 10
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2013_10_4_a10/
ID  - CSIS_2013_10_4_a10
ER  - 
%0 Journal Article
%A Peter Hancox
%A Nikolaos Polatidis
%T An evaluation of keyword, string similarity and very shallow syntactic matching for a university admissions processing infobot
%J Computer Science and Information Systems
%D 2013
%V 10
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2013_10_4_a10/
%F CSIS_2013_10_4_a10
Peter Hancox; Nikolaos Polatidis. An evaluation of keyword, string similarity and very shallow syntactic matching for a university admissions processing infobot. Computer Science and Information Systems, Tome 10 (2013) no. 4. http://geodesic.mathdoc.fr/item/CSIS_2013_10_4_a10/