PANDA: A platform for academic knowledge discovery and acquisition

摘要: Scientific literatures contain some academic knowledge which is interesting or valuable but previously unknown. For instance, an algorithm A proposed in one article might have association with B another article, while designed based on the definition of C a third article. Thus we can deduce relationship A-C A-B and B-C. There are also other kinds such as between two research communities, historical evolvement topics, etc. But exponential growth articles that usually published Portable Document Format (PDF), to discover acquire potential poses many practical challenges. Existing algorithmic methods hardly extend handle diverse journals layouts, nor scale up process massive documents. As crowdsourcing has become powerful paradigm for problem-solving especially tasks difficult computer resolve solely, state problem discovery acquisition using hybrid framework, integrating accuracy human workers speed automatic algorithms. We briefly introduce Platform Academic kNowledge Discovery Acquisition (PANDA), our current system implementation, well preliminary achievements promising future directions.