Enhanced Text Analytics Using Lifted Probabilistic Inference Algorithms

ABSTRACT: LVI proposes developing an advanced framework of lifted probabilistic inference algorithms for enhancing the scaling and accuracy of text analytics. In Phase I of this project, LVI proposes to explore the scalability of various lifted inference techniques for utilizing Markov Logic Networks (MLN) and the Tractable Markov Logic language in the Tuffy software package as a base platform. These techniques will be applied to the area of automated knowledge base construction from free text, using abductive reasoning to infer the optimal updates to the knowledge base. The MLN will use unsupervised joint inferencing techniques to combine record segmentation, co-reference resolution, and entity resolution in a single process, as opposed to a pipelined approach. Phase I will also include a cost-benefit analysis of utilizing ontologies as background knowledge as a method of bootstrapping MLN learning, using general-purpose models from Linked Open Data (LOD) Cloud sources such as DBpedia and YAGO. LVI's proposed solution is based on the company's extensive experience in developing tools utilizing Semantic Web based AI technologies, inference engines, and Linked Data applications. LVI brings deep experience in knowledge engineering, information extraction, data integration through statistical ontology alignment, machine learning, and online analytical processing (OLAP), and intelligent application development. BENEFIT: The algorithms for Lifted inference have a variety of applications. They include Social networks, object recognition, link prediction, activity recognition, model counting, bio-medical applications and relational reasoning and learning. Fundamental building block to improve current capabilities.