WordGraph - Development of a unified graph-theoretical system for acquiring lexico-semantic phenomena

• Applicant: Professor Dr. Hinrich Schütze
• Subject Area: General and Comparative Linguistics, Experimental Linguistics, Typology, Non-European Languages
• Term: from 2007 to 2018
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 42840215

• Final Report Year: 2018

Final Report Abstract

We achieved good results for several of the research questions that were the subject of this proposal and published them in the top venues of our field. The most important ones are the following two: - Our inability to compute similarity efficiently for large graphs had been a big problem initially. That we were able to solve it by creating CoSimRank was an important breakthrough. - We were able to integrate traditional computational linguistics (the WordNet graph) and modern embedding technology into a common formal framework. We published several resources that will be helpful for future research on graphs and embedding in natural language processing.