Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
This work addresses a specific bottleneck in natural language processing for tasks like information extraction, but it is incremental as it builds on existing neural network approaches.
The paper tackled the problem of irrelevant information in long-distance subject-object pairs for semantic relation classification by using a convolutional neural network on the shortest dependency path and a negative sampling strategy, achieving state-of-the-art results on the SemEval-2010 Task 8 dataset.
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. Experimental results show that our method outperforms the state-of-the-art methods on the SemEval-2010 Task 8 dataset.