Udo Hahn, Kornél Markó, and Stefan Schulz
Using language technology for text analysis and light-weight ontologies as a content-mediating level, we acquire indexing patterns from vast amounts of indexing data for English-language medical documents. This is achieved by statistically relating interlingual representations of these documents (based on text token bigrams) to their associated index terms. From these "English" indexing patterns, we then induce the associated index terms for German and Portuguese documents when their interlingual representations match those of English documents. Thus, we learn from past English indexing experience and transfer it in an unsupervised way to non-English texts, without ever having seen concrete indexing data for languages other than English.