Increasing the Effectiveness of the Romanian Wordnet in NLP Applications

摘要

The Romanian wordnet is a semantic network under ceaseless enrichment and improvement. Its use in various applications throughout time highlighted the need for further development. In this paper we focus on a question answering scenario. We show how adding derivational relations between the literals already present in the network could help increase the effectiveness of using the Romanian wordnet in such an application. We describe the steps we took in the process of identifying, validating and adding derivational relations in our network and then simulate a question answering situation using RoWikipedia as corpus.