TY - CONF T1 - NeurAlign: combining word alignments using neural networks T2 - Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing Y1 - 2005 A1 - Ayan,Necip Fazil A1 - Dorr, Bonnie J A1 - Monz,Christof AB - 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. JA - Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing T3 - HLT '05 PB - Association for Computational Linguistics CY - Stroudsburg, PA, USA UR - http://dx.doi.org/10.3115/1220575.1220584 M3 - 10.3115/1220575.1220584 ER -