Document-level Neural MT: A Systematic Comparison

Autor: António Lopes, Amin Farajian, M., Rachel Bawden, Michael Zhang, André Martins

Publikováno v: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
22nd Annual Conference of the European Association for Machine Translation
22nd Annual Conference of the European Association for Machine Translation, 2020, Lisboa, Portugal. pp.225-234
HAL
Lopes, A V, Farajian, M A, Bawden, R, Zhang, M & Martins, A F T 2020, Document-level Neural MT: A Systematic Comparison . in Proceedings of the 22nd Annual Conference of the European Association for Machine Translation . Lisboa, Portugal, pp. 225–234, 22nd Annual Conference of the European Association for Machine Translation, 3/11/20 . < https://eamt2020.inesc-id.pt/proceedings-eamt2020.pdf >

International audience; In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions. As part of this comparison, we introduce and evaluate a document-level variant of the recently proposed

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4c18403fc1561ebc38c82cd096d6fd2d
https://hal.archives-ouvertes.fr/hal-02900686/document

Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing

Autor: Gonçalo M. Correia, António V. Lopes, Jonay Trénous, M. Amin Farajian, André F. T. Martins

Publikováno v: WMT (3)

This paper describes Unbabel's submission to the WMT2019 APE Shared Task for the English-German language pair. Following the recent rise of large, powerful, pre-trained models, we adapt the BERT pretrained model to perform Automatic Post-Editing in a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e72aae6159b55aed7f9e7b322c33652b
http://arxiv.org/abs/1905.13068

Neural vs. Phrase-Based Machine Translation in a Multi-Domain Scenario

Autor: Matteo Negri, Marcello Federico, Nicola Bertoldi, Marco Turchi, M. Amin Farajian

Publikováno v: EACL (2)

State-of-the-art neural machine translation (NMT) systems are generally trained on specific domains by carefully selecting the training sets and applying proper domain adaptation techniques. In this paper we consider the real world scenario in which

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::92085c29a62bff33977bf2afee332b52
https://doi.org/10.18653/v1/e17-2045

Online Word Alignment for Online Adaptive Machine Translation

Autor: Marcello Federico, M. Amin Farajian, Nicola Bertoldi

Publikováno v: HaCaT@EACL

A hot task in the Computer Assisted Translation scenario is the integration of Machine Translation (MT) systems that adapt sentence after sentence to the postedits made by the translators. A main role in the MT online adaptation process is played by

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d802b91bd65aaba4727598be6f6d164c
https://doi.org/10.3115/v1/w14-0313

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.