Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Chiara Argese"'
Publikováno v:
Nordlyd: Tromsø University Working Papers on Language & Linguistics, Vol 46, Iss 1 (2022)
Machine learning is the dominating paradigm in natural language processing nowadays. It requires vast amounts of manually annotated or synthetically generated text data. In the GiellaLT infrastructure, on the other hand, we have worked with rule-base
Externí odkaz:
https://doaj.org/article/1063afdd01b14ca0b9106b2ea873221b
Publikováno v:
Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it 2020 ISBN: 9791280136336
CLiC-it
Scopus-Elsevier
CLiC-it
Scopus-Elsevier
Lexicalizing compounds, in addition to treating them dynamically, is a key element in giving us idiomatic translations and detecting compound errors. We present and evaluate an e-dictionary (NDS) and a grammar checker (GramDivvun) for North Sámi. We
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0e75cdb9470ae7373330b012c009df6
http://books.openedition.org/aaccademia/8979
http://books.openedition.org/aaccademia/8979
Publikováno v:
RANLP
We investigate both rule-based and machine learning methods for the task of compound error correction and evaluate their efficiency for North Sami, a low resource language. The lack of error-free data needed for a neural approach is a challenge to th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff4806500e13009d353512b020d417f4
https://doi.org/10.26615/978-954-452-072-4_171
https://doi.org/10.26615/978-954-452-072-4_171
Autor:
Chiara Argese, Trond Trosterud
Publikováno v:
Septentrio Conference Series; No 2 (2017): UiT Digital Humanities Conference 2017
Presentation given at UiT Digital Humanities Conference 2017
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d1379a92d3d5ec29b617d454e67d037
https://doi.org/10.7557/5.4678
https://doi.org/10.7557/5.4678
Publikováno v:
Journal of Geophysical Research: Space Physics. 121:6307-6323
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb7616f9ada68ed0f379cf17cb65e7f5
https://doi.org/10.1002/2015ja022041
https://doi.org/10.1002/2015ja022041