English

Empirical Methods for Compound Splitting

Computation and Language 2007-05-23 v1

Abstract

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.

Keywords

Cite

@article{arxiv.cs/0302032,
  title  = {Empirical Methods for Compound Splitting},
  author = {Philipp Koehn and Kevin Knight},
  journal= {arXiv preprint arXiv:cs/0302032},
  year   = {2007}
}

Comments

8 pages, 2 figures. Published at EACL 2003