A neural approach to language variety translation

Ruiz Costa-Jussà, Marta; Zampieri, Marcos; Pal, Santanu

View/Open

document(5).pdf (131,0Kb) (Restricted access) Request copy

View Usage Statistics

Cita com:

Show full item record

Ruiz Costa-Jussà, Marta

Zampieri, Marcos

Pal, Santanu

Document typeConference lecture

Defense date2018

PublisherAssociation for Computational Linguistics

Rights accessRestricted access - publisher's policy

Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain

Abstract

In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language. We take the pair Brazilian - European Portuguese as an example and compare the performance of this method to a phrase-based statis- tical machine translation system. We report a performance improvement of 0.9 BLEU points in translating from European to Brazilian Portuguese and 0.2 BLEU points when translating in the opposite direction. We also carried out a human evaluation experiment with native speakers of Brazilian Portuguese which indicates that humans prefer the output produced by the neural-based system in comparison to the statistical system

CitationRuiz, M., Zampieri, M., Pal, S. A neural approach to language variety translation. A: International Conference on Computational Linguistics. "COLING 2018: The 27th International Conference on Computational Linguistics: Proceedings of the Conference: August 20-26, 2018 Santa Fe, New Mexico, USA". Stroudsburg, PA: Association for Computational Linguistics, 2018.

URIhttp://hdl.handle.net/2117/125675

ISBN978-1-948087-50-6

Collections

View Usage Statistics

Show full item record

Files	Description	Size	Format	View
document(5).pdf		131,0Kb	PDF	Restricted access

UPCommons. Global access to UPC knowledge

A neural approach to language variety translation

View/Open

Browse