Natural Language Processing

Our interest is in statistical natural-language processing, which uses stochastic, probabilistic and statistical methods to resolve some of the difficulties in making human language accessible to computational systems. Longer sentences are highly ambiguous when processed with realistic grammars, yielding thousands or millions of possible analyses, which makes heuristic methods impractical. So, we're utilizing corpora, specialized lexical parsing and support vector machines to solve the problem of natural language understanding by computers.

Why This Matters

People are producing petabytes of new textual data daily. This data is meaningless unless we can find what we're looking for. Our mission is to help categorize and filter textual data so we can access, publish and consume data in a meaningful way.