The German EU Council Presidency Translator

Autor: Josef van Genabith, Stephan Busemann, Artūrs Vasiļevskis, Mārcis Pinnis

Publikováno v: KI - Künstliche Intelligenz. 36:99-104

This contribution describes the German EU Council Presidency Translator (EUC PT), a machine translation service created for the German EU Council Presidency in the second half of 2020, which is open to the general public. Following a series of earlie

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::baec78737f0ddcd08ee8e06e49adfc7f
https://doi.org/10.1007/s13218-021-00744-4

Open and Competitive Multilingual Neural Machine Translation in Production

Autor: Andre Tättar, Taido Purason, Hele-Andra Kuulmets, Agnes Luhtaru, Liisa Rätsep, Maali Tars, Mārcis Pinnis, Toms Bergmanis, Mark Fishel

Publikováno v: Baltic Journal of Modern Computing. 10

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::76382522c23b86bcfd315a2cb7eaeef4
https://doi.org/10.22364/bjmc.2022.10.3.15

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

Autor: Toms Bergmanis, Arturs Stafanovics, Mārcis Pinnis

Publikováno v: Baltic HLT

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: https://explore.openaire.eu/search/publication?articleId=doi_________::ab0cf44c73cbf3b224943c5e6f5b1aa4
https://doi.org/10.3233/faia200606

Data Augmentation for Pipeline-Based Speech Translation

Autor: Diego Alves, Mārcis Pinnis, Askars Salimbajevs

Publikováno v: Human Language Technologies – The Baltic Perspective-Proceedings of the Ninth International Conference Baltic HLT 2020
Scopus-Elsevier
Baltic HLT
9th International Conference on Human Language Technologies-the Baltic Perspective (Baltic HLT 2020)
9th International Conference on Human Language Technologies-the Baltic Perspective (Baltic HLT 2020), Sep 2020, Kaunas, Lithuania
Frontiers in Artificial Intelligence and Applications
Frontiers in Artificial Intelligence and Applications-Human Language Technologies – The Baltic Perspective

International audience; Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ac1c7b2e9f2562da26949be95b6d01c

Extracting Data from Comparable Corpora

Autor: Mārcis Pinnis, Nikola Ljubešić, Inguna Skadiņa, Tatjana Gornostaja, Špela Vintar, Darja Fišer, Marko Tadić, Dan Stefanescu

Publikováno v: Using Comparable Corpora for Under-Resourced Areas of Machine Translation ISBN: 9783319990033
Using Comparable Corpora for Under-Resourced Areas of Machine Translation

Comparable corpora may comprise different types of single-word and multi-word phrases that can be considered as reciprocal translations, which may be beneficial for many different natural language processing tasks. This chapter describes methods and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c8f31fc81d3de2dcbe75b06e778fbe37
https://doi.org/10.1007/978-3-319-99004-0_4