Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Michael Ustaszewski"'
Autor:
Andy Stauder, Michael Ustaszewski
Publikováno v:
Studia Translatorica, Iss 11, Pp 177-188 (2020)
In audiovisual translation, stylometry can be used to measure formal-aesthetic fidelity. We present a corpus-based measure of syntactic complexity as a feature of language style. The methodology considers hierarchical dimensions of syntactic complexi
Externí odkaz:
https://doaj.org/article/d86f7db8da12496d980a99f0203af590
Autor:
Michael Ustaszewski
Publikováno v:
Translation Studies. 14:313-331
Despite its importance in a globalized world, indirect translation is a peripheral and under-researched topic in translation studies. Existing research on indirect translation is almost exclusively...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a74433972ca57bf83898d18f2849818a
https://doi.org/10.1080/14781700.2021.1894226
https://doi.org/10.1080/14781700.2021.1894226
Testing the validity of Wikipedia categories for subject matter labelling of open-domain corpus data
Publikováno v:
Journal of Information Science. 48:686-700
The Wikipedia category system was designed to enable browsing and navigation of Wikipedia. It is also a useful resource for knowledge organisation and document indexing, especially using automatic approaches. However, it has received little attention
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7747662f02e7558a5e6f8f8b7e26ad42
https://doi.org/10.1177/0165551520977438
https://doi.org/10.1177/0165551520977438
Publikováno v:
Digital Scholarship in the Humanities. 36:1-15
The extraction of large amounts of multilingual parallel text from web resources is a widely used technique in natural language processing. However, automatically collected parallel corpora usually lack precise metadata, which are crucial to accurate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b611ecea1da880deeb56ed47443e86af
https://doi.org/10.1093/llc/fqaa002
https://doi.org/10.1093/llc/fqaa002
Autor:
Emmanuelle Esperança-Rodier, Laurent Besacier, Jakob Verbeek, Francis Brunet-Manquat, Maha Elbayad, Michael Ustaszewski
Publikováno v:
COLING
COLING 2020-28th International Conference on Computational Linguistics
COLING 2020-28th International Conference on Computational Linguistics, Dec 2020, Virtual, Spain. pp.5047-5058, ⟨10.18653/v1/2020.coling-main.443⟩
COLING 2020-28th International Conference on Computational Linguistics
COLING 2020-28th International Conference on Computational Linguistics, Dec 2020, Virtual, Spain. pp.5047-5058, ⟨10.18653/v1/2020.coling-main.443⟩
We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attention (Elbayad et al. 2018) and attention-based Transformer (Vaswani et al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a942401ed33297ac8f642cbb09535b57
https://doi.org/10.18653/v1/2020.coling-main.443
https://doi.org/10.18653/v1/2020.coling-main.443
Autor:
Michael Ustaszewski
Publikováno v:
Perspectives. 27:107-123
The freely available European Parliament Proceedings Parallel Corpus, or Europarl, is one of the largest multilingual corpora available to date. Surprisingly, bibliometric analyses show that it has...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::84a29badb2a5ca9fb8980bec2fb95457
https://doi.org/10.1080/0907676x.2018.1485716
https://doi.org/10.1080/0907676x.2018.1485716
Autor:
Michael Ustaszewski
Publikováno v:
Proceedings of the Second Workshop Human-Informed Translation and Interpreting Technology associated with RANLP 2019.
Neural machine translation (NMT) was shown to produce more fluent output than phrase-based statistical (PBMT) and rule-based machine translation (RBMT). However, improved fluency makes it more difficult for post editors to identify and correct adequa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::597185c435ee2114a41501a0160502c9
https://doi.org/10.26615/issn.2683-0078.2019_015
https://doi.org/10.26615/issn.2683-0078.2019_015
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783030279462
TSD
TSD
Sentence-aligned parallel bilingual corpora are the main and sometimes the only required resource for training Statistical and Neural Machine Translation systems. We propose an end-to-end deep neural architecture for sentence alignment. In addition t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::627131e40a0915961a27086e9d2f4a2b
https://doi.org/10.1007/978-3-030-27947-9_16
https://doi.org/10.1007/978-3-030-27947-9_16
Die Beiträge dieses Bandes geben Auskunft, wie Forschung und Lehre am Institut für Translationswissenschaft (INTRAWI) aufgestellt sind, um mit der Entwicklung der Translationsbranche Schritt zu halten. Die fortschreitende Globalisierung und Digital
TRANSLATA II was the second in a series of triennial conferences on Translation and Interpreting Studies, held at the University of Innsbruck. The series is conceptualized as a forum for Translation Studies research. The contributions to this volume