%0 Conference Paper %B Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing %D 2005 %T NeurAlign: combining word alignments using neural networks %A Ayan,Necip Fazil %A Dorr, Bonnie J %A Monz,Christof %X 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. %B Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing %S HLT '05 %I Association for Computational Linguistics %C Stroudsburg, PA, USA %P 65 - 72 %8 2005/// %G eng %U http://dx.doi.org/10.3115/1220575.1220584 %R 10.3115/1220575.1220584