On the Power of Massive Text Data

The real-world big data is largely unstructured, dynamic, and interconnected, in the form of natural language text. It is highly desirable to transform such massive unstructured data into structured knowledge. Many researchers and practitioners rely on labor-intensive labeling and curation to extract knowledge from unstructured text data. However, such approaches may not be scalable to web-scale or adaptable to new domains, especially considering that a lot of text corpora are highly dynamic and domain-specific. We argue that massive text data itself contains a large body of hidden patterns, structures, and knowledge. Equipped with domain-independent and domain-specific knowledge-bases, a promising direction is to develop more systematic data mining methods to turn massive unstructured text data into structured knowledge. We introduce a set of methods developed recently in our own group on exploration of the power of big text data, including mining quality phrases using unsupervised, weakly supervised and distantly supervised approaches, recognition and typing of entities and relations by distant supervision, meta-pattern-based entity-attribute-value extraction, set expansion and local embedding-based multi-faceted taxonomy discovery, allocation of text documents into multi-dimensional text cubes, construction of heterogeneous information networks from text cube, and eventually mining multi-dimensional structured knowledge from massive text data. We show that massive text data itself can be powerful at disclosing patterns, structures and hidden knowledge, and it is promising to explore the power of massive, interrelated text data for transforming such unstructured data into structured knowledge.