1 |
The CLASSLA-StanfordNLP model for lemmatisation of standard Slovenian 1.4
|
|
|
|
BASE
|
|
Show details
|
|
2 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.3
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multiword Expressions lexicon extracted from the Gigafida 2.1 corpus
|
|
|
|
BASE
|
|
Show details
|
|
5 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.2
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The CLASSLA-StanfordNLP model for lemmatisation of standard Slovenian 1.3
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Frequency lists of collocations from the Gigafida 2.1 corpus
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Enhancing deep neural networks with morphological information ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Dependency tree extraction tool STARK 1.0
|
|
Krsnik, Luka; Dobrovoljc, Kaja; Robnik-Šikonja, Marko. - : Centre for Language Resources and Technologies, University of Ljubljana, 2019. : Faculty of Arts, University of Ljubljana, 2019. : Faculty of Computer and Information Science, University of Ljubljana, 2019
|
|
BASE
|
|
Show details
|
|
11 |
Corpus extraction tool LIST 1.2
|
|
Krsnik, Luka; Arhar Holdt, Špela; Čibej, Jaka. - : Centre for Language Resources and Technologies, University of Ljubljana, 2019. : Faculty of Computer and Information Science, University of Ljubljana, 2019. : Jožef Stefan Institute, 2019
|
|
BASE
|
|
Show details
|
|
12 |
Corpus extraction tool LIST 1.0
|
|
Krsnik, Luka; Arhar Holdt, Špela; Čibej, Jaka. - : Centre for Language Resources and Technologies, University of Ljubljana, 2019. : Faculty of Computer and Information Science, University of Ljubljana, 2019. : Jožef Stefan Institute, 2019
|
|
BASE
|
|
Show details
|
|
13 |
Automatically stress labelled morphological lexicon Sloleks 1.2, version 1.1
|
|
|
|
Abstract:
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 in two ways: information about stress location only, and information about stress location and type. Stress assignment was performed automatically, with algorithms based on deep neural networks which correctly predicted accent location in 91.5% and combined accent type and location in 88.5% of test data. Therefore not all accents are correct. This updated 1.1 version of the lexicon contains stress asignments with an improved algorithm, which reduces the error by about 1% against the previous 1.0 version.
|
|
Keyword:
Slovenian language; word stress
|
|
URL: http://hdl.handle.net/11356/1186
|
|
BASE
|
|
Hide details
|
|
14 |
Automatically stress labelled morphological lexicon Sloleks 1.2
|
|
|
|
BASE
|
|
Show details
|
|
|
|