Document Content Processing

The Document Content Processing program takes XRCE's expertise in natural language processing to develop customer-pulled technologies to support the access, management and processing of natural language information in a multi-lingual and multi format context.

Components of this program bridge the gap between document and knowledge, by extracting information from documents, providing access to the information, promoting document sharing, enriching documents with existing information and structuring information.

The Document Content Processing program will is built upon the accumulated skills and technologies in the following areas; Entity and fact extraction; Categorisation and clustering; Finite State based Natural Language Processing; Linguistic Resources; Cross Lingual Information Retrieval and Summarization and XML Multilingual Document Authoring.

Projects and activities

Several projects and activities are done in direct relation with this program. All these projects are to be delivered according to precise requirements and milestones, with Business Groups or external companies as customer.

• Classification
• Information Extraction
• XML Conversion
• Datamining