Word Alignment Step by Step

Abstract

In this paper the current stage o f the Uppsala Word Aligner (UWA) is described.The system is developed within the project on parallel texts, PLUG, which has its focus on the analysis o f bi-lingual text collections with Swedish either as the source or the target language.UWA comprises a set o f knowledgelite approaches' for word alignment and lexicon extraction.A distinctive feature is its modularity.In the article, the main principles o f the alignment software are introduced, different configurations and approaches are described, and examples o f alignment results are presented.