TechNet (http://www.tech-net.org) consists of >4 million technology-related terms and their semantic relations. The terms are retrieved from unstructured texts in ~6 million USPTO patents and their pairwise semantic relations are calculated using a neural network language model. TechNet outperforms Google Knowledge Graph, ConceptNet, and WordNet for engineering technical text analysis. It can serve as an infrastructure to support a wide range of AI applications in the context of engineering and technology.
Our team won the "Best Paper Award" at 31st International Conference on Design Theory & Methodology, Anaheim, California, for a new method to evaluate design concepts using machine learning & natural language processing
Professor Jianxi Luo received SUTD's "Excellence in Research" Award, 2018