Bridging linguistic typology and multilingual machine translation with multi-view language representations

Arturo Oncevay, Barry Haddow, Alexandra Birch

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

19 Citas (Scopus)

Resumen

Sparse language vectors from linguistic typology databases and learned embeddings from tasks like multilingual machine translation have been investigated in isolation, without analysing how they could benefit from each other's language characterisation. We propose to fuse both views using singular vector canonical correlation analysis and study what kind of information is induced from each source. By inferring typological features and language phylogenies, we observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy in tasks that require information about language similarities, such as language clustering and ranking candidates for multilingual transfer. With our method, which is also released as a tool, we can easily project and assess new languages without expensive retraining of massive multilingual or ranking models, which are major disadvantages of related approaches.

Idioma originalInglés
Título de la publicación alojadaEMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
EditorialAssociation for Computational Linguistics (ACL)
Páginas2391-2406
Número de páginas16
ISBN (versión digital)9781952148606
EstadoPublicada - 2020
Publicado de forma externa
Evento2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020 - Virtual, Online
Duración: 16 nov. 202020 nov. 2020

Serie de la publicación

NombreEMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Conferencia

Conferencia2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020
CiudadVirtual, Online
Período16/11/2020/11/20

Huella

Profundice en los temas de investigación de 'Bridging linguistic typology and multilingual machine translation with multi-view language representations'. En conjunto forman una huella única.

Citar esto