Usaar-wlv: Hypernym generation with deep neural nets

Li Ling Tan, Rohit Gupta, Josef van Genabith

In: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015). International Workshop on Semantic Evaluation (SemEval-2015) 9th June 4-5 Denver Colorado United States 2015.


his paper describes the USAAR-WLV taxonomy induction system that participated in the Taxonomy Extraction Evaluation task of SemEval-2015. We extend prior work on using vector space word embedding models for hypernym-hyponym extraction by simplifying the means to extract a projection matrix that transforms any hyponym to its hypernym. This is done by making use of function words, which are usually overlooked in vector space approaches to NLP. Our system performs best in the chemical domain and has achieved competitive results in the overall evaluations.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence