Natural Language Processing
Enabling machines to understand and respond to what people mean, so they can interact with a computer naturally – without having to adapt their behavior to a computer's limitations.

Resolving ambiguities in written and spoken language requires analyzing grammar, concepts, context, and human knowledge. For example:

"The company is ready to sell” is not easy for a computer to understand because the sentence is syntactically ambiguous – is the company opening for business, or does it want to be acquired?

Resolving this ambiguity requires understanding the context: is the sentence in the middle of an article on mergers and acquisitions? Or is the sentence followed by “Its shelves are stocked with all the hot products"? This succeeding sentence is helpful only if the computer understands that the possessive pronoun “its” refers to the company, and that “stocked” and “products” are more relevant to selling goods than to being acquired.

PARC Approach & Applications

PARC researchers have been solving a series of increasingly difficult challenges in natural language understanding for over thirty years.

Going beyond purely statistical or machine-learning techniques, PARC's linguistic theories, algorithms, and engineering platforms provide multiple levels of meaning extraction – from language analysis, to logic and deep knowledge representation in multiple languages. Example contributions and applications include:
-	XLE – a broad-based, high-speed parsing and generation engine for a variety of languages, that includes a rewrite system that can process parser output into deep semantic and knowledge representation structures; and
-	Finite state toolkit – a highly efficient text analytics technology for entity extraction and pattern matching.

Current work includes:

• high-performance search engine – for semantically-based information retrieval across enterprise document repositories and e-discovery applications
   
• question-answering system – that uses entailment and contradiction logic to answer actual questions instead of providing only matching documents.

Examples — abstract knowledge representation