Abstract
Translation of named-entities (NEs) is an issue in SMT. In this paper we analyze the errors when translating NEs with a SMT system from English to Spanish. We train on Europarl and test on News Commentary, focusing on entities correctly recognized by an automatic NE recognition system. The automatic systems translate around 85% NEs correctly, leaving a small margin for improving performance. In addition, we implement a purpose-build NE translator and integrate it in the SMT system, yielding a small but significant improvement in BLEU score. Our analysis shows that, contrary to similar systems translating from Chinese to English, there was no improvement in NE translation, prompting further work.
Cite
CITATION STYLE
Artetxe, M., Agirre, E., Alegria, I., & Labaka, G. (2015). Analyzing English-Spanish Named-Entity enhanced Machine Translation. In Proceedings of SSST 2015: 9th Workshop on Syntax, Semantics and Structure in Statistical Translation - NAACL HLT 2015 / SIGMT / SIGLEX Workshop (pp. 52–54). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/w15-1007
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
