Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

Understand

Syntactic features play an essential role in identifying relationship in a sentence.

• Previous neural network models often suffer from irrelevant information introduced when subjects and objects are in a long distance.
• In this paper, we propose to learn more robust relation representations from the shortest dependency path through a convolution neural network.
• We further propose a straightforward negative sampling strategy to improve the assignment of subjects and objects.