Relation Extraction Releases
Type-Aware Distantly Supervised Relation Extraction with Linked Arguments
Mitchell Koch, John Gilmer, Stephen Soderland, Daniel S. Weld. Accepted to the Conference on Empirical Methods in Natural Language Processing, 2014. [paper]
GoReCo Relation Extractor Evaluation
GoReCo is a new gold standard evaluation for relation extraction consisting of exhaustive annotations of the 128 documents from ACE 2004 newswire for 48 relations. The code and data are available on GitHub. It requires the original ACE 2004 download from the LDC.
This is a framework for distantly supervised relation extraction that handles corpus representation, distant supervision, feature generation, model training, and extraction. The code is available on GitHub. It is based on the MultiR project.
Available upon request.