Computer Science – Computation and Language
Scientific paper
2003-02-22
Computer Science
Computation and Language
8 pages, 2 figures. Published at EACL 2003
Scientific paper
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.
Knight Kevin
Koehn Philipp
No associations
LandOfFree
Empirical Methods for Compound Splitting does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Empirical Methods for Compound Splitting, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Empirical Methods for Compound Splitting will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-668406