Automatically stress labelled morphological lexicon Sloleks 1.2

  Authors

Krsnik, Luka ; Robnik-Šikonja, Marko and Šef, Tomaž

  Item identifier

http://hdl.handle.net/11356/1156

 Project URL

https://github.com/lkrsnik/simple_accentuation

 Referenced by

http://videolectures.net/jota_krsnik_napovedovanje_naglasa/
https://repozitorij.uni-lj.si/IzpisGradiva.php?id=98276

 Date issued

2017-09-26

 Type

lexicalConceptualResource, text

 Size

2774745 words, 100805 entries

 Language(s)

Slovenian

 Description

This lexicon is an extended version of Sloleks 1.2 (http://hdl.handle.net/11356/1039). It contains all the original data from Sloleks with added information about the stress of each word form, which is included two ways: information about stress location only, and information about stress location and type. The stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in around 90 % and combined accent type and location in about 87.5 % of test data. Therefore all accents are not correct.

 Publisher

Faculty of Computer and Information Science, University of Ljubljana

 Subject(s)

word stress

 Collection(s)

CLARIN.SI data & tools

 

This item is replaced by a newer submission:

http://hdl.handle.net/11356/1186

List all versions  

Show full item record