@article{Ahmed2010, abstract = {The SLIF project combines text-mining and image processing to extract structured information from biomedical literature.SLIF extracts images and their captions from published papers. The captions are automatically parsed for relevant biological entities (protein and cell type names), while the images are classified according to their type (e.g., micrograph or gel). Fluorescence microscopy images are further processed and classified according to the depicted subcellular localization.The results of this process can be queried online using either a user-friendly web-interface or an XML-based web-service. As an alternative to the targeted query paradigm, SLIF also supports browsing the collection based on latent topic models which are derived from both the annotated text and the image data.The SLIF web application, as well as labeled datasets used for training system components, is publicly available at http://slif.cbi.cmu.edu.}, author = {Ahmed, Amr and Arnold, Andrew and Coelho, Luis Pedro and Kangas, Joshua and Sheikh, Abdul-Saboor and Xing, Eric P. and Cohen, William W. and Murphy, Robert F.}, doi = {10.1016/j.websem.2010.04.002}, journal = {Journal of Web Semantics}, month = {jan}, pages = {151-154}, title = {Structured Literature Image Finder: Parsing Text and Figures in Biomedical Literature}, url = {http://repository.cmu.edu/cgi/viewcontent.cgi?article=1040&context=machine_learning}, volume = {8}, year = {2010} }