Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Matīss Rikters"'
Publikováno v:
International Journal of Food Design, Vol 6, Iss 2, Pp 181-212 (2021)
How a food, or a dish, is named and how its components and attributes are described can all influence the perception and the enjoyment of the food. Therefore, tracing patterns in food descriptions and determining their role can be of value. The aims
Externí odkaz:
https://doaj.org/article/346f9debe3b04dba87102e30f7010b7c
Publikováno v:
Eesti ja Soome-ugri Keeleteaduse Ajakiri, Vol 13, Iss 1 (2022)
This article describes linguistic collections of Livonian, development of digital resources, and their usage. The main motivation is to ensure the accessibility of Livonian intangible cultural heritage and linguistic materials for the Livonian and re
Externí odkaz:
https://doaj.org/article/cc0b5aeaa92d412e8162748c06fb5261
Publikováno v:
Journal of Natural Language Processing. 28:380-403
Publikováno v:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
Autor:
Matīss Rikters, Sanita Reinsone
Publikováno v:
Baltic Journal of Modern Computing. 10
Publikováno v:
IEEE Access, Vol 12, Pp 23-33 (2024)
We introduce BERT-NAR-BERT (BnB) – a pre-trained non-autoregressive sequence-to-sequence model, which employs BERT as the backbone for the encoder and decoder for natural language understanding and generation tasks. During the pre-training and fine
Externí odkaz:
https://doaj.org/article/a335ee9967c840cc815b66b50cc44d11
Autor:
Sproģis, Uga, Matīss Rikters
We present the Latvian Twitter Eater Corpus - a set of tweets in the narrow domain related to food, drinks, eating and drinking. The corpus has been collected over time-span of over 8 years and includes over 2 million tweets entailed with additional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2f1f321d1e0a5df43f7aa430c38b65f
Publikováno v:
WAT@EMNLP-IJCNLP
While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues rem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e7ada48e32f8345010f8ffebba1fca4
Autor:
Matīss Rikters
Publikováno v:
Baltic Journal of Modern Computing. 7
Publikováno v:
WMT (2)
The paper describes the development process of Tilde’s NMT systems for the WMT 2019 shared task on news translation. We trained systems for the English-Lithuanian and Lithuanian-English translation directions in constrained and unconstrained tracks