The automatic generation of dictionaries from raw text has previously been based on parallel or comparable corpora. Here we describe an approach requiring only a single monolingual corpus to generate bilingual dictionaries for several language pairs. A constraint is that all language pairs have their target language in common, which needs to be the language of the underlying corpus. Our approach is based on the observation that monolingual corpora usually contain a considerable number of foreign words. As these are often explained via translations typically occurring close by, we can identify these translations by looking at the contexts of a foreign word and by computing its strongest associations from these. In this work we focus on the question what results can be expected for 20 language pairs involving five major European languages. We also compare the results for two different types of corpora, namely newsticker texts and web corpora. Our findings show that results are best if English is the source language, and that noisy web corpora are better suited for this task than well edited newsticker texts.
展开▼
