Empirical Methods for Compound Splitting
arXiv:cs/0302032
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.
8 pages, 2 figures. Published at EACL 2003
Cited by in corpus (5)
- Fast Domain Adaptation for Neural Machine Translation
- Pre-Translation for Neural Machine Translation
- Comparing Neural- and N-Gram-Based Language Models for Word Segmentation
- Splitting Compounds by Semantic Analogy
- Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words