Mining Structures of Factual Knowledge from Text An Effort-Light Approach Synthesis Lectures on Data Mining and Knowledge Discovery Series

The real-world data, though massive, is largely unstructured, in the form of natural-language text. It is challenging but highly desirable to mine structures from massive text data, without extensive human annotation and labeling. In this book, we investigate the principles and methodologies of mining structures of factual knowledge (e.g., entities and their relationships) from massive, unstructured text corpora. Departing from many existing structure extraction methods that have heavy reliance on human annotated data for model training, our effort-light approach leverages human-curated facts stored in external knowledge bases as distant supervision and exploits rich data redundancy in large text corpora for context understanding. This effort-light mining approach leads to a series of new principles and powerful methodologies for structuring text corpora, including (1) entity recognition, typing and synonym discovery, (2) entity relation extraction, and (3) open-domain attribute-valuemining and information extraction. This book introduces this new research frontier and points out some promising research directions.

Acknowledgments.- Introduction.- Background.- Literature Review.- Entity Recognition and Typing with Knowledge Bases.- Fine-Grained Entity Typing with Knowledge Bases.- Synonym Discovery from Large Corpus.- Joint Extraction of Typed Entities and Relationships.- Pattern-Enhanced Embedding Learning for Relation Extraction.- Heterogeneous Supervision for Relation Extraction.- Indirect Supervision: Leveraging Knowledge from Auxiliary Tasks.- Mining Entity Attribute Values with Meta Patterns.- Open Information Extraction with Global Structure Cohesiveness.- Open Information Extraction with Global Structure Cohesiveness.- Applications.- Conclusions.- Vision and Future Work.- Bibliography.- Authors' Biographies.

Xiang Ren is an Assistant Professor in the Department of Computer Science at USC, affiliated faculty at USC ISI, and a part-time data science advisor at Snap Inc. At USC, Xiang is part of the Machine Learning Center, NLP community, and Center on Knowledge Graphs. Prior to that, he was a visiting researcher at Stanford University, and received his Ph.D. in Computer Science from University of Illinois at Urbana-Champaign. His research develops computational methods and systems that extract machine-actionable knowledge from massive unstructured data (e.g., text data), and particular focuses on problems in the space of modeling sequence and graph data under weak supervision (learning with partial/noisy labels, and semi-supervised learning) and indirect supervision (multi-task learning, transfer learning, and reinforcement learning). Xiang's research has been recognized with several prestigious awards including a Yahoo!-DAIS Research Excellence Award, a Yelp Dataset Challenge award, a C. W. Gear Outstanding Graduate Student Award and a David J. Kuck Outstanding M.S. Thesis Award. Technologies he developed have been transferred to U.S. Army Research Lab, National Institute of Health, Microsoft, Yelp, and TripAdvisor.