Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Vassilina Nikoulina"'
Publikováno v:
Proceedings of the 21st Workshop on Biomedical Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb4f0c51bb01aaa83780d30e11bbef9f
https://doi.org/10.18653/v1/2022.bionlp-1.5
https://doi.org/10.18653/v1/2022.bionlp-1.5
Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at inference
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33cf6eba8b0d0bda40e46dea4ab3ec14
http://arxiv.org/abs/2109.06679
http://arxiv.org/abs/2109.06679
Publikováno v:
Findings of ACL 2021
Findings of ACL 2021, Aug 2021, Bangkok (virtual), Thailand
ACL/IJCNLP (Findings)
Findings of ACL 2021, Aug 2021, Bangkok (virtual), Thailand
ACL/IJCNLP (Findings)
Recent studies on the analysis of the multilingual representations focus on identifying whether there is an emergence of language-independent representations, or whether a multilingual model partitions its weights among different languages. While mos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94dd4f6101b864eed9d32b21072295ee
https://hal.archives-ouvertes.fr/hal-03299010/file/Do_Multilingual_Neural_Machine_Translation_Models_Contain_Language_Pair_Specific_Cross_Attention_Heads_-2.pdf
https://hal.archives-ouvertes.fr/hal-03299010/file/Do_Multilingual_Neural_Machine_Translation_Models_Contain_Language_Pair_Specific_Cross_Attention_Heads_-2.pdf
Autor:
Vassilina Nikoulina, Maxat Tezekbayev, Nuradil Kozhakhmet, Madina Babazhanova, Matthias Gallé, Zhenisbek Assylbekov
There is an ongoing debate in the NLP community whether modern language models contain linguistic knowledge, recovered through so-called probes. In this paper, we study whether linguistic knowledge is a necessary condition for the good performance of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d1e1ae8b72966cdf13e3e53f3b07acd
http://arxiv.org/abs/2103.01819
http://arxiv.org/abs/2103.01819
Publikováno v:
Proceedings of the 2nd Workshop on Computational Approaches to Discourse.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a2c7b975e3f048b1eabbeb3af30d084
https://doi.org/10.18653/v1/2021.codi-main.16
https://doi.org/10.18653/v1/2021.codi-main.16
Publikováno v:
NLP4COVID@EMNLP
We release a multilingual neural machine translation model, which can be used to translate text in the biomedical domain. The model can translate from 5 languages (French, German, Italian, Korean and Spanish) into English. It is trained with large am
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::776e5ebde2f6c2a4c94b2a18a95dd00e
Autor:
Claude Roux, Ioan Calapodescu, Jean-Luc Meunier, Alexandre Berard, Vassilina Nikoulina, Marc Dymetman
Publikováno v:
NGT@EMNLP-IJCNLP
We share a French-English parallel corpus of Foursquare restaurant reviews (https://europe.naverlabs.com/research/natural-language-processing/machine-translation-of-restaurant-reviews), and define a new task to encourage research on Neural Machine Tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::231293763925a7093bc87fd0c3b094af
http://arxiv.org/abs/1910.14589
http://arxiv.org/abs/1910.14589
Publikováno v:
NGT@EMNLP-IJCNLP
Exploiting large pretrained models for various NMT tasks have gained a lot of visibility recently. In this work we study how BERT pretrained models could be exploited for supervised Neural Machine Translation. We compare various ways to integrate pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::496266d541fb272aa5a4f6753c2323e9
Autor:
Vassilina Nikoulina, Caroline Brun
Publikováno v:
WASSA@EMNLP
In this paper, we test state-of-the-art Aspect Based Sentiment Analysis (ABSA) systems trained on a widely used dataset on actual data. We created a new manually annotated dataset of user generated data from the same domain as the training dataset, b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::75e368fe88e6dd7a900471a4f2ec4642
https://doi.org/10.18653/v1/w18-6217
https://doi.org/10.18653/v1/w18-6217
Publikováno v:
EACL
We propose a demonstration of a domainspecific terminology checking service which works on top of any generic blackbox MT, and only requires access to a bilingual terminology resource in the domain. In cases where an incorrect translation of a source
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2d373e70964ca21dfa48efea23e37f3
https://doi.org/10.3115/v1/e14-2013
https://doi.org/10.3115/v1/e14-2013