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.
|Publisher||Association for Computational Linguistics|
|Conference||Tenth Conference on European Chapter of the Association for Computational Linguistics (EACL '03)|
|Period||12/04/03 → 17/04/03|