Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Bergmanis, Toms"'
Autor:
Bergmanis, Toms, Pinnis, Mārcis
In this paper, we examine the development and usage of six low-resource machine translation systems translating between the Ukrainian language and each of the official languages of the Baltic states. We developed these systems in reaction to the esca
Externí odkaz:
http://arxiv.org/abs/2209.14142
Autor:
Lagzdiņš, Andis, Siliņš, Uldis, Pinnis, Mārcis, Bergmanis, Toms, Vasiļevskis, Artūrs, Vasiļjevs, Andrejs
Consolidated access to current and reliable terms from different subject fields and languages is necessary for content creators and translators. Terminology is also needed in AI applications such as machine translation, speech recognition, informatio
Externí odkaz:
http://arxiv.org/abs/2207.06729
Autor:
Bergmanis, Toms, Pinnis, Mārcis
The majority of language domains require prudent use of terminology to ensure clarity and adequacy of information conveyed. While the correct use of terminology for some languages and domains can be achieved by adapting general-purpose MT systems on
Externí odkaz:
http://arxiv.org/abs/2109.04708
Autor:
Bergmanis, Toms, Pinnis, Mārcis
Most of the recent work on terminology integration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the target language sentence. In day-to-day work of professional translator
Externí odkaz:
http://arxiv.org/abs/2101.10035
When translating "The secretary asked for details." to a language with grammatical gender, it might be necessary to determine the gender of the subject "secretary". If the sentence does not contain the necessary information, it is not always possible
Externí odkaz:
http://arxiv.org/abs/2010.06203
Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are used to t
Externí odkaz:
http://arxiv.org/abs/2009.05460
Autor:
Bergmanis, Toms, Goldwater, Sharon
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sen
Externí odkaz:
http://arxiv.org/abs/1904.01464
Autor:
TĀTTAR, Andre, PURASON, Taido, KUULMETS, Hele-Andra, LUHTARU, Agnes, RATSEP, Liisa, TARS, Maali, PINNIS, Mārcis, BERGMANIS, Toms, FISHEL, Mark
Publikováno v:
Baltic Journal of Modern Computing; 2022, Vol. 10 Issue 3, p422-434, 13p
Autor:
Bergmanis, Toms
A core issue that hampers development and use of language technology for underresourced and morphologically rich languages is data sparsity. In this work, we consider unsupervised morphological analysis and lemmatization — two linguistically motiva
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______463::ca65bcdfec65c94e6300cb253d8a3799
https://hdl.handle.net/1842/37115
https://hdl.handle.net/1842/37115
Autor:
Bergmanis, Toms, Goldwater, Sharon
Publikováno v:
Bergmanis, T & Goldwater, S 2019, Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text . in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : Volume 1 (Long and Short Papers) . pp. 4119–4128, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, United States, 2/06/19 . https://doi.org/10.18653/v1/N19-1418
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3094::701bcd8a7fad70981cb8c906d9a99a93
https://www.pure.ed.ac.uk/ws/files/97173573/Data_Augmentation_for_Context_Sensitive_BERGMANIS_DoA220219_VoR_CC_BY.pdf
https://www.pure.ed.ac.uk/ws/files/97173573/Data_Augmentation_for_Context_Sensitive_BERGMANIS_DoA220219_VoR_CC_BY.pdf