DE eng

Search in the Catalogues and Directories

Hits 1 – 8 of 8

1
Word-embedding based bilingual terminology alignment ...
BASE
Show details
2
Aligning Estonian and Russian news industry keywords with the help of subtitle translations and an environmental thesaurus ...
Repar, Andraž; Shumakov, Andrej. - : Zenodo, 2021
BASE
Show details
3
Word-embedding based bilingual terminology alignment ...
BASE
Show details
4
Aligning Estonian and Russian news industry keywords with the help of subtitle translations and an environmental thesaurus ...
Repar, Andraž; Shumakov, Andrej. - : Zenodo, 2021
BASE
Show details
5
Corpus of Written Standard Slovene Gigafida 2.0
Krek, Simon; Erjavec, Tomaž; Repar, Andraž. - : Centre for Language Resources and Technologies, University of Ljubljana, 2021
BASE
Show details
6
SimLex-999 Slovenian translation SimLex-999-sl 1.0
Pollak, Senja; Vulić, Ivan; Pelicon, Andraž. - : University of Ljubljana, 2021
BASE
Show details
7
Evaluation of contextual embeddings on less-resourced languages ...
Abstract: The current dominance of deep neural networks in natural language processing is based on contextual embeddings such as ELMo, BERT, and BERT derivatives. Most existing work focuses on English; in contrast, we present here the first multilingual empirical comparison of two ELMo and several monolingual and multilingual BERT models using 14 tasks in nine languages. In monolingual settings, our analysis shows that monolingual BERT models generally dominate, with a few exceptions such as the dependency parsing task, where they are not competitive with ELMo models trained on large corpora. In cross-lingual settings, BERT models trained on only a few languages mostly do best, closely followed by massively multilingual BERT models. ... : 45 pages ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2107.10614
https://dx.doi.org/10.48550/arxiv.2107.10614
BASE
Hide details
8
Reproduction, replication, analysis and adaptation of a term alignment approach [<Journal>]
Repar, Andraž [Verfasser]; Martinc, Matej [Verfasser]; Pollak, Senja [Verfasser]
DNB Subject Category Language
Show details

Catalogues
0
0
0
0
1
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
7
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern