Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Mikel Artetxe"'
Round-trip Machine Translation (MT) is a popular choice for paraphrase generation, which leverages readily available parallel corpora for supervision. In this paper, we formalize the implicit similarity function induced by this approach, and show tha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11400a6617421b066cf5a72301cb4050
Publikováno v:
Computational Linguistics, Vol 45, Iss 3, Pp 395-421 (2019)
This article describes a compositional distributional method to generate contextualized senses of words and identify their appropriate translations in the target language using monolingual corpora. Word translation is modeled in the same way as conte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3927750c6dfc9e8f9a15fd99ee4fd0c4
https://doi.org/10.1162/coli_a_00353
https://doi.org/10.1162/coli_a_00353
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on monolingua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18fa9f316f6a001582d38fca2978a19b
http://arxiv.org/abs/2105.10419
http://arxiv.org/abs/2105.10419
Autor:
Nicola De Cao, Ledell Wu, Kashyap Popat, Mikel Artetxe, Naman Goyal, Mikhail Plekhanov, Luke Zettlemoyer, Nicola Cancedda, Sebastian Riedel, Fabio Petroni
We present mGENRE, a sequence-to-sequence system for the Multilingual Entity Linking (MEL) problem -- the task of resolving language-specific mentions to a multilingual Knowledge Base (KB). For a mention in a given language, mGENRE predicts the name
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4612eccc299ed697a433db2c325d76f
http://arxiv.org/abs/2103.12528
http://arxiv.org/abs/2103.12528
Publikováno v:
EMNLP (1)
Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test set or the t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c640f8aa781349f28818fc51fd9c8657
http://arxiv.org/abs/2004.04721
http://arxiv.org/abs/2004.04721
Publikováno v:
ACL
We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for many of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a9f554de1fb54efe507383f456a48e6
https://doi.org/10.18653/v1/2020.acl-main.658
https://doi.org/10.18653/v1/2020.acl-main.658
Back-translation provides a simple yet effective approach to exploit monolingual corpora in Neural Machine Translation (NMT). Its iterative variant, where two opposite NMT models are jointly trained by alternately using a synthetic parallel corpus ge
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0346a26633f84084b21e4608d29a1bef
Publikováno v:
EACL
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based on language-specific encoder-de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0add1acb46564d645d9260b30ea2f78c
Publikováno v:
Scopus-Elsevier
ACL (1)
ACL (1)
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest nei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c75d39acecce3f913f7eec465a687491
Publikováno v:
ACL
State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. This generalization ability has been attributed to the use of a shared subword vocabulary and joint traini
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c4fc418d198a8980eeb61635f504739