Multilingwis – A Multilingual Search Tool for Multi-Word Units in Multiparallel Corpora

We describe a web-based application for searching translations of multi-word units in large, openly available multiparallel corpora. This web application offers a unique resource for multilingual terminologists and translators. The first edition of the tool covers the debates of the European Parliament in five languages: English, French, German, Italian, and Spanish. Our search tool provides a simple and intuitive user interface, which optimally supports content-oriented queries while relieving the user from specifying complicated search expressions in a complex query language. We describe the necessary automatic preprocessing steps of the linguistic data, the retrieval component, and the techniques needed for offering a zero configuration search