Empirical Methods for Compound Splitting

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact on performance of statistical MT systems. Results show accuracy of 99.1% and performance gains for MT of 0.039 BLEU on a German-English noun phrase translation task.
8 pages, 2 figures. Published at EACL 2003

Keywords

Computation and Language, I.2.7

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/31477

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0302032
 http://arxiv.org/abs/cs/0302032

Collections

arXiv