Welcome to the Text Analysis and Language Engineering Group which is part of the Knowledge Management Technology Department at  the Thomas J. Watson Research Center of  IBM Research.

We analyze the contents of  large document collections using scaleable NLP techniques to extract information and  produce artifacts reflecting the lexical and conceptual content of these documents. We use  the extracted information in applications which help people get value from document collections including:

• Refining queries
• Navigating through important concepts in the domain
• Browsing through document space
• Visualizing concepts and key information
• Presenting summaries and other document highlights
• and other knowledge management applications