Combination of Statistical Word Alignments Based on Multiple Preprocessing Schemes

We present an approach to using multiple preprocessing schemes to improve statistical word alignments. We show a relative reduction of alignment error rate of about 38%.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Jakob Elming, Nizar Habash
• Keywords: Alignment Error Rate, Computational Linguistics, Multiple Preprocessing Schemes, NAACL 2007, Statistical Word Alignments