Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures

    EMNLP, pp. 2588-2597, 2017.

    Cited by: 16|Bibtex|Views16|Links
    EI

    Abstract:

    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

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments