Software Campus Projekt: LICORES
LICORES: Linking unstructured content to domain-specific knowledge repositories using contextualized distributional semantics
The project LICORES copes with the research and the development of methods, that can be used to align new knowledge into existing ontologies. Therefore, we focus on methods of distributional semantics that can be directly applied to text. Furthermore, we also want to focus on methods which allow to annotate the knowledge of an ontology back into a new text.
Software Campus
Software Campus is funded by Germany's Federal Ministry for Education and Research (BMBF). In close collaboration with strong partners from industry and research, Software Campus participants develop innovative academic IT projects and benefit from an individually tailored training curriculum with outstanding academics and managers. The Federal Ministry of Education and Research (BMBF) provides funding of up to EUR 100,000 for each IT project.
External Partners
- Siemens Corporate Technology
- Ulli Waltinger
- Michael Skubacz
People
- Chris Biemann: academic partner
- Martin Riedl: project leader
- Eugen Ruppert: executive staff
Publications
- Martin Riedl, Chris Biemann (2015): A Single Word is not Enough: Ranking Multiword Expressions Using Distributional Semantics. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015). Lisboa, Portugal (pdf,README)
- Lucie Flekova, Eugen Ruppert and Daniel Preotiuc-Pietro (2015):Analysing Domain Suitability of a Sentiment Lexicon by Identifying Distributionally Bipolar Words. In: Association for Computational Linguistics: Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, p. 77-84, Lisboa, Portugal (pdf)
- Tim Feuerbach, Martin Riedl, Chris Biemann (2015): Distributional Semantics for Resolving Bridging Mentions. In: Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP '15), Hissar, Bulgaria (pdf,slides,source contribution,source bansal klein)
- Eugen Ruppert, Jonas Klesy, Martin Riedl, Chris Biemann (2015): Rule-based Dependency Parse Collapsing and Propagation for German and English. In: Proceedings of the GSCL 2015. Duisburg, Germany (pdf)
- Eugen Ruppert, Manuel Kaufmann, Martin Riedl, Chris Biemann (2015): JOBIMVIZ: A Web-based Visualization for Graph-based Distributional Semantic Models. In the Annual Meeting of the Association for Computational Linguistics (ACL) System Demonstrations, Beijing, China (pdf)
- Martin Riedl, Irina Alles, Chris Biemann (2014), Combining Supervised and Unsupervised Parsing for Distributional Similarity. In Proceedings of COLING 2014. Dublin, Ireland (pdf,slides)