Semantic Retrieval

MultiLexExplorer_screenshot Current search engines have become an essential tool for the majority of Web users. Nevertheless, certain fundamental properties leave room for improvement. For instance, from a linguistic point of view, current information retrieval systems could benefit from lexical and grammatical resources with sufficient coverage for general, i.e. not domain specific or restricted, text. Furthermore, linguistic Information (e.g. semantics) can help users in specifying the meaning of their query for retrieving only the relevant documents related to it. 

In our research, we focus especially on methods for supporting the user in browsing and navigating the different meanings of a word. Therefore, word sense disambiguation and performant clustering- and classification methods play an important role for building such an interactive multilingual retrieval system.

Publications

Last Modification: 01.03.2018 - Contact Person: