Paper: NeurAlign: Combining Word Alignments Using Neural Networks

ACL ID H05-1009
Title NeurAlign: Combining Word Alignments Using Neural Networks
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors

This paper presents a novel approach to combining different word alignments. We view word alignment as a pattern classifi- cation problem, where alignment combi- nation is treated as a classifier ensemble, and alignment links are adorned with lin- guistic features. A neural network model is used to learn word alignments from the individual alignment systems. We show that our alignment combination approach yields a significant 20-34% relative er- ror reduction over the best-known align- ment combination technique on English- Spanish and English-Chinese data.