RUC. Repositorio da Universidade da Coruña
Publication
Contribución de congreso (ConferenceOutput)
Exploring cross-lingual word embeddings for the inference of bilingual dictionaries
Paper included in:
Proceedings of TIAD-2019 Shared Task – Translation Inference Across Dictionaries
co-located with the 2nd Language, Data and Knowledge Conference (LDK 2019)
Leipzig, Germany, May 20, 2019., [Abstract]: We describe four systems to generate automatically bilingual
dictionaries based on existing ones: three transitive systems differing only
in the pivot language used, and a system based on a different approach
which only needs monolingual corpora in both the source and target
languages. All four methods make use of cross-lingual word embeddings
trained on monolingual corpora, and then mapped into a shared vector space. Experimental results confirm that our strategy has a good
coverage and recall, achieving a performance comparable to to the best
submitted systems on the TIAD 2019 gold standard set among the teams
participating at the TIAD shared task., Research supported by a 2017 Leonardo Grant for Researchers and Cultural Creators (BBVA Foundation), by Ministerio de Economía, Industria y Competitividad (Grant TIN2017-85160-C2-1-R), and by Xunta de Galicia (Grant ED431B-2017/01). Marcos Garcia has been funded by a Juan de la Cierva grant (IJCI-2016-29598), and Marcos García-Salido by a post-doctoral grant from Xunta de Galicia (ED481D 2017/009).
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research., Xunta de Galicia; ED481D 2017/009, Xunta de Galicia; ED431B-2017/01