Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Orhan Firat"'
Autor:
Damla Yüce, Ertuğrul Avşar, Hasan Güner, Altan Yilmaz, Gökhan Arasan, Orhan Firat, Kemal Ayğan
Publikováno v:
International Journal of Engineering and Geosciences, Vol 5, Iss 3, Pp 160-168 (2020)
Volume: 5, Issue: 3 160-168
International Journal of Engineering and Geosciences
Volume: 5, Issue: 3 160-168
International Journal of Engineering and Geosciences
Optical satellite imagery has an important place today in terms of responding to the increasing need for geospatial base in many different fields and disciplines, especially because of their availability and temporal resolution. Because all kinds of
Autor:
Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages. XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval. Covering 102 langua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d5112276248b7b6fa2427d9ed857587
Autor:
Sebastian Ruder, Noah Constant, Jan Botha, Aditya Siddhant, Orhan Firat, Jinlan Fu, Pengfei Liu, Junjie Hu, Dan Garrette, Graham Neubig, Melvin Johnson
Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year. For example, the latest techniques have improved the state-of-the-art performance on the XTREME multilingual benchmark by more
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::971d36ebc711e18e4116896239f94bcc
http://arxiv.org/abs/2104.07412
http://arxiv.org/abs/2104.07412
Publikováno v:
NAACL-HLT
We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation. Our approach is suitable f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a006a913ed729108b58f6c794f1a055a
http://arxiv.org/abs/2103.06799
http://arxiv.org/abs/2103.06799
Publikováno v:
NAACL-HLT
Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages, unsupervi
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily available. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4969ea8b265a7546b3c3dc08a3d513ad
Publikováno v:
NAACL-HLT
Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) and XLMR (Conneau et al., 2020) have proven to be impressively effective at enabling transfer-learning of NLP systems from high-resource languages to low-resource languages. This
In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing the same text in another language. We propose an end-to-end neural model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2444f0aaf25c00d8b75130cc82691bfd
Autor:
Ankur Bapna, Yuan Cao, Aditya Siddhant, Mia Xu Chen, Sneha Kudugunta, Orhan Firat, Naveen Arivazhagan, Yonghui Wu
Publikováno v:
ACL
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via multilingual NMT. The
Publikováno v:
SPNLP@EMNLP
Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate sequence-to-sequence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37fa3b3d3a16d0b32e51887cbf9cd5cb