Paper: Alignment Link Projection Using Transformation-Based Learning

ACL ID H05-1024
Title Alignment Link Projection Using Transformation-Based Learning
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

We present a new word-alignment ap- proach that learns errors made by ex- isting word alignment systems and cor- rects them. By adapting transformation- based learning to the problem of word alignment, we project new alignment links from already existing links, using features such as POS tags. We show that our align- ment link projection approach yields a sig- nificantly lower alignment error rate than that of the best performing alignment sys- tem (22.6% relative reduction on English- Spanish data and 23.2% relative reduction on English-Chinese data).