Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition

This paper proposes a novel framework called bilingual co-training for a largescale, accurate acquisition method for monolingual semantic knowledge. In this framework, we combine the independent processes of monolingual semanticknowledge acquisition for two languages using bilingual resources to boost performance. We apply this framework to largescale hyponymy-relation acquisition from Wikipedia. Experimental results show that our approach improved the F-measure by 3.6–10.3%. We also show that bilingual co-training enables us to build classifiers for two languages in tandem with the same combined amount of data as required for training a single classifier in isolation while achieving superior performance.