Extracting the Science from Scientific Publications

This is an edited version of the original project proposal. This proposal is for a collaboration between three groups in Cambridge. The Computer Laboratory (CL) group provides expertise in Natural Language Processing (NLP), the Chemistry group brings in a user-base as well as experience in application of NLP technology to eScience goals, while the Cambridge eScience Centre (CesC) will ensure scalability and integration of the technology. The project also involves three publishers as partners, who will support the project by supplying large corpora of scientific papers, providing informal feedback and facilitating dissemination activities: the Royal Society of Chemistry, Nature Publishing Group and the International Union of Crystallography. Project objectives: