Inferring semantic types of the entity mentions in a sentence is a necessary yet challenging task. Most ofexisting methods employ a very coarse-grained type taxonomy, which is too general and not exact enough for many tasks.However, the performances of the methods drop sharply when we extend the type taxonomy to a fine-grained one with severalhundreds of types. In this paper, we introduce a hybrid neural network model for type classification of entity mentions witha tine-grained taxonomy. There are four components in our model, namely, the entity mention component, the contextcomponent, the relation component, the already known type component, which are used to extract features from the targetentity mention, context, relations and already known types of the entity mentions in surrounding context respectively. Thelearned features by the four components are concatenated and fed into a softmax layer to predict the type distribution.We carried out extensive experiments to evaluate our proposed model. Experimental results demonstrate that our modelachieves state-of-the-art performance on the FIGER dataset. Moreover, we extracted larger datasets from Wikipedia andDBpedia. Oil the larger datasets, out＇ model achieves the comparable performance to the state-of-the-art methods with thecoarse-grained type taxonomy, but performs much better than those methods with the fine-grained type taxonomy in terinsof micro-F1, macro-F1 and weighted-F1.
展开▼
