Text mining is used in a variety of ways to identify and extract information from documents. Using Natural Language Processing (NLP) with text mining, data may be extracted to reveal facts and relationships that provide directly relevant information to address specific questions. Incorporating ChemAxon JChem with chemical ontologies allows for substructure and similarity searches to supplement the NLP searches. The talk will provide insight into ways chemical data from a variety of sources such as patents and full-text journal articles can be text-mined.

Download Daniel's presentation slides & Jeff's presentation slides