Hyunmin Cheong, Wei Li, Adrian Cheung, Andy Nogueira, Francesco Iorio
Hyunmin Cheong, Wei Li, Adrian Cheung, Andy Nogueira, Francesco Iorio
Nominated for Ford Best Paper Award at Design Automation Conference
ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
2015
This paper presents a method to automatically extract function knowledge from natural language text. Our method uses syntactic rules to extract subject-verb-object triplets from parsed text. We then leverage the Functional Basis taxonomy, WordNet, and word2vec to classify the triplets as artifact-function-energy flow knowledge. For evaluation, we compare the function definitions associated with 30 most frequent artifacts compiled in a human-constructed knowledge base, Oregon State University’s Design Repository (DR), to those extracted using our method from 4953 Wikipedia pages classified under the category “Machines”. Our method found function definitions for 66% of the test artifacts. For those artifacts found, our method identified 50% of the function definitions compiled in DR. In addition, 75% of the most frequent function definitions found by our method were also defined in DR. The results demonstrate the promising potential of our method in automatic extraction of function knowledge.
Loading...
What if a CAD system could generate thousands of design options that all meet your specified goals? It’s no longer what if: it’s Project Dreamcatcher, the next generation of CAD. Dreamcatcher is a generative design system that enables designers to craft a definition of their design problem through goals and constraints. This information is used to synthesize alternative design solutions that meet the objectives. Designers are able to explore trade-offs between many alternative approaches and select design solutions for manufacture.