TXM

Synopsis

Text Mining for Biomedical Content Curation

Description

TXM is a three year collaborative R&D programme funded by ITI Lifesciences, and is being carried out jointly with Cognia EU Ltd, a new subsidiary of US-based biological and chemical information management company Cognia.

The natural language processing components of the system fall broadly into four areas:

Document Retrieval, using text categorization to determine whether a document is curatable.
Named Entity Recognition
Term Identification
Relation Extraction