Detail publikace

Language-Independent Text Classifier Base on Recurrent Neural Networks

MYŠKA, V.

Originální název

Language-Independent Text Classifier Base on Recurrent Neural Networks

Anglický název

Language-Independent Text Classifier Base on Recurrent Neural Networks

Jazyk

en

Originální abstrakt

This paper deals with a proposal of language independent text classifiers based on recurrent neural networks. They work at a character level thus they do not require any text preprocessing. The classifiers have been trained and evaluated on a multilingual data set that is privately collected from film review databases. It contains Czech (Slovak), English, German and Spanish language subset. The resulting accuracy of the proposed language independent classifiers base on the recurrent neural networks in polarity sentiment analysis task is 78.55%.

Anglický abstrakt

This paper deals with a proposal of language independent text classifiers based on recurrent neural networks. They work at a character level thus they do not require any text preprocessing. The classifiers have been trained and evaluated on a multilingual data set that is privately collected from film review databases. It contains Czech (Slovak), English, German and Spanish language subset. The resulting accuracy of the proposed language independent classifiers base on the recurrent neural networks in polarity sentiment analysis task is 78.55%.

Dokumenty

BibTex


@inproceedings{BUT157417,
  author="Vojtěch {Myška}",
  title="Language-Independent Text Classifier Base on Recurrent Neural Networks",
  annote="This paper deals with a proposal of language independent text classifiers based on recurrent neural networks. They work at a character level thus they do not require any text preprocessing. The classifiers have been trained and evaluated on a multilingual data set that is privately collected from film review databases. It contains Czech (Slovak), English, German and Spanish language subset. The resulting accuracy of the proposed language independent classifiers base on the recurrent neural networks in polarity sentiment analysis task is 78.55%.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  booktitle="Proceedings of the 25th Conference STUDENT EEICT 2019",
  chapter="157417",
  howpublished="online",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  year="2019",
  month="april",
  pages="754--758",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  type="conference paper"
}