Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

Abstract

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.

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (7)

• Joint entity recognition and relation extraction as a multi-head selection problem
• Classifying medical relations in clinical text via convolutional neural networks
• BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformer
• Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network
• Stochastic Learning of Nonstationary Kernels for Natural Language Modeling
• REflex: Flexible Framework for Relation Extraction in Multiple Domains
• Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting