Diacritics Restoration Using Deep Neural Networks
- 1 August 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Diacritics restoration problem is defined as correct insertion of diacritic marks into a sentence without changing the context of a particular sentence. Changing a letter in a text can cause the meaning of the word to change, and therefore the meaning of the whole sentence. This kind of problem is common among languages that use Latin alphabet such as the Slovak language. Our goal is to develop an artificial neural network that can restore diacritic errors made by a human or a computer. For this purpose, we chose state of the art architecture of recurrent neural network. Our results prove that neural network is able to restore diacritics with 97 % accuracy on given Slovak corpus. The accuracy test on a text from a different genre, however, has shown a lower accuracy of 76%.Keywords
This publication has 12 references indexed in Scilit:
- Sentiment analysis of social network posts in Slovak languagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Diacritics Restoration in the Slovak Texts Using Hidden Markov ModelPublished by Springer Nature ,2016
- Automatic diacritization of Arabic text using recurrent neural networksInternational Journal on Document Analysis and Recognition (IJDAR), 2015
- Automatic Diacritics Restoration for HungarianPublished by Association for Computational Linguistics (ACL) ,2015
- Arabic Diacritization with Recurrent Neural NetworksPublished by Association for Computational Linguistics (ACL) ,2015
- Vowel and Diacritic Restoration for Social Media TextsPublished by Association for Computational Linguistics (ACL) ,2014
- Hybrid speech recognition with Deep Bidirectional LSTMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Automatic Diacritic Restoration for Resource-Scarce LanguagesLecture Notes in Computer Science, 2007
- Confusion Matrix VisualizationPublished by Springer Nature ,2004
- Long Short-Term MemoryNeural Computation, 1997