Publication Details

BUTknot at SemEval-2016 task 5: Supervised machine learning with term substitution approach in Aspect Category Detection

MACHÁČEK Jakub. BUTknot at SemEval-2016 task 5: Supervised machine learning with term substitution approach in Aspect Category Detection. In: SemEval 2016 - 10th International Workshop on Semantic Evaluation. San Diego: Association for Computational Linguistics, 2016, pp. 301-305. ISBN 978-1-941643-95-2. Available from: https://www.aclweb.org/anthology/S16-1048/
Czech title
VUTknot na SemEval-2016 úkol 5: Dohled nad strojovým učením s termínovým substitučním přístupem
Type
conference paper
Language
english
Authors
Macháček Jakub, Bc. (RCIT FIT BUT)
URL
Keywords

supervised learning, semantics, learninig systems, information retrieval, artifiacl intelligence

Abstract

This paper describes an approach used to solve Aspect Category Detection (Subtask 1, Slot 1) of SemEval 2016 Task 5. The core of the presented system is based on Supervised machine learning using bigram bag-of-words model. The performance is enhanced by several preprocessing methods, most importantly by a term substitution technique. The system has reached a very good performance in comparison with other submitted systems.

Published
2016
Pages
301-305
Proceedings
SemEval 2016 - 10th International Workshop on Semantic Evaluation
Conference
10th International Workshop on Semantic Evaluation, San Diego, US
ISBN
978-1-941643-95-2
Publisher
Association for Computational Linguistics
Place
San Diego, US
DOI
10.18653/v1/S16-1048
EID Scopus
2-s2.0-85035748508
BibTeX 
@INPROCEEDINGS{FITPUB12261,
   author = "Jakub Mach\'{a}\v{c}ek",
   title = "BUTknot at SemEval-2016 task 5: Supervised machine learning with term substitution approach in Aspect Category Detection",
   pages = "301--305",
   booktitle = "SemEval 2016 - 10th International Workshop on Semantic Evaluation",
   year = 2016,
   location = "San Diego, US",
   publisher = "Association for Computational Linguistics",
   ISBN = "978-1-941643-95-2",
   doi = "10.18653/v1/S16-1048",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12261"
}
Back to top