Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures
EMNLP, pp. 2588-2597, 2017.
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities_of_residence) for a given entity from a large collection of source documents. In this paper we propose an effective DNN architecture for SF with the following new strategies: (1). Take a regularized dependency graph instead of a ra...More