MultiLexExplorer

MultiLexExplorer_screenshot

MultiLexExplorer is a tool that combines a knowledge-driven word sense disambiguation with a knowledge-based text retrieval approach in an interactive framework. We use lexical resources in order to disambiguate documents (retrieved from the web or a local document collection) given the different meanings (retrieved from the lexical resources, in our case EuroWordNet) of a search term having unambiguous description in different languages. We focus especially on the integration of methods that support the adaptation of the system interface and the output to the current search context.

Using EuroWordNet for cross-language text retrieval, we support the user in:

  • exploring the linguistic context of a word in the general hierarchy,
  • searching in different languages, e.g., by translating word senses using the interlingual index of EuroWordNet,
  • disambiguating the word senses of different word combinations,
  • interacting with the system changing the search context "center" of the original query and, thus, also the search words and the number of retrieved results,
  • expanding the original query to restrict the number of retrieved documents, and in
  • categorizing the retrieved web documents automatically using different categorization methods.

Related Publications

  • Ernesto William De Luca, Martin Eul and Andreas Nürnberger: Multilingual Query-Reformulation using an RDF-OWL EuroWordNet Representation. In: Proceedings of the Workshop on Improving Web retrieval for non-English queries (iNEWS07). In conjunction with the SIGIR 2007 Konferenz, Amsterdam, 2007.
  • Ernesto William De Luca and Andreas Nürnberger: Using clustering methods to improve ontology-based query term disambiguation, Int. Journal of Intelligent Systems, 21:7, pp. 693-709, 2006.
  • Ernesto William De Luca, Stefan Hauke, Andreas Nürnberger and Stefan Schlechtweg: Using Multilingual Ontologies for Adaptive Web-based Language Exploration. In: Proceedings of the International Workshop on Applications of Semantic Web Technologies for E-Learning (SW-EL06). In conjunction with the International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems (AH2006), pp. 35-44, 2006.
  • Ernesto William De Luca, Stefan Hauke, Andreas Nürnberger and Stefan Schlechtweg: MultiLexExplorer: Combining Multilingual Web Search with Multilingual Lexical Resources, in: Charles Callaway, Andrea Corradini, Jörn Kreutel, Johanna Moore und Manfred Stede (Edts.), Proc. of Combined Workshop on Language-Enabled Educational Technology and Development and Evaluation of Robust Spoken Dialogue Systems (part of ECAI 2006), pp.: 17-21, 2006.

Last Modification: 01.03.2018 - Contact Person:

Sie können eine Nachricht versenden an: Prof. Dr.-Ing. Andreas Nürnberger
Sicherheitsabfrage:
Captcha
 
Lösung: