Abstract
Relation Extraction is an important task in natural language processing (NLP) and Knowledge Base (KB) constructing. Distant Supervision (DS) is a widely used technique for automatically labeling training data by aligning the triples in a KB with free text. However, most methods treat DS relational extraction as a classification problem, which are vulnerable to dataset distribution. In this paper, we propose a retrieval-based method based on piecewise convolutional neural networks (called RPCNN) for DS relation extraction, which calculate relation retrieval scores between input features and relation features before classification. We apply knowledge embedding learning model to learn relation feature vectors from the KB used in DS, which means that our model could leverage the semantic knowledge in the KB to improve the relation extraction. Experimental results on widely used datasets show that our RPCNN model outperform all the baseline systems.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
