Abstract

We present a method to align words in a bitext that combines elements of a traditional statistical approach with linguistic knowledge. We demonstrate this approach for Arabic-English, using an alignment lexicon produced by a statistical word aligner, as well as linguistic resources ranging from an English parser to heuristic alignment rules for function words. These linguistic heuristics have been generalized from a development corpus of 100 parallel sentences. Our aligner, UALIGN, outperforms both the commonly used GIZA++ aligner and the state-of-theart LEAF aligner on F-measure and produces superior scores in end-to-end statistical machine translation,+ 1.3 BLEU points over GIZA++, and+ 0.7 over LEAF.

Date

2009

Authors

Ulf Hermjakob

Conference

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

Pages

229-237