|Title||NeurAlign: combining word alignments using neural networks|
|Publication Type||Conference Paper|
|Year of Publication||2005|
|Authors||Ayan, NF, Dorr, BJ, Monz, C|
|Conference Name||Conference on Human Language Technology and Empirical Methods in Natural Language Processing|
|Publisher||Association for Computational Linguistics|
|Conference Location||Vancouver, British Columbia, Canada|
This paper presents a novel approach to combining different word alignments. We view word alignment as a pattern classification problem, where alignment combination is treated as a classifier ensemble, and alignment links are adorned with linguistic 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 error reduction over the best-known alignment combination technique on English-Spanish and English-Chinese data.