Empirical Methods for Compound Splitting

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.

• Type: Conference
• Year: 2003
• Where: EACL
• Authors: Philipp Koehn, Kevin Knight
• Keywords: EACL 2003, German-English Noun Phrase, Natural Language Processing, Parallel Corpora, Statistical Mt Systems