In this paper, a word alignment approach is presented which is based on a combination of clues. Word alignment clues indicate associations between words and phrases. They can be based on features such as frequency, part-of-speech, phrase type, and the actual wordform strings. Clues can be found by calculating similarity measures or learned from word aligned data. The clue alignment approach...

Recent years have seen a few serious attempts to develop methods and measures for the evaluation of word alignment systems, notably the Blinker project (Melamed, 1998) and the ARCADE project (Vronis and Langlais, forthcoming). In this paper we discuss different approaches to the problem and report on results from a project where two word alignment systems have been evaluated. These results include methods and tools for the generation of reference data and a set of measures for system performance. We note that the selection and sampling of reference data can have a great impact on scoring results.

This paper focuses on the improvement of automatically generated phrase lists by applying word alignment approaches to parallel bitext. Such phrase lists, in terms of multi-word collocations, serve several tasks such as the compilation of terminology databases or translation database in the multilingual case. Our investigations are based on the assumption that word alignment favors well-formed phrase structures rather than irregular text segments. If this is the case, word alignment will lter out irregular structures from automatically generated phrase lists. As a result, an improved phrase list may be compiled based on the bilingual lexicon that could be extracted. Furthermore, word alignment approaches can be used to identify additional multi-word units by comparing corresponding multiword units from the bitext. Our investigations will be focused on a Swedish/English text collection that has been aligned with the Uppsala Word Aligner (UWA). 1 Introduction Domain specic terminolog...