Finding important information in unstructured text
From Language and Information Technologies
Jump to: navigation, search
A vast majority of the information we deal with in everyday life consists of raw, unstructured text, where the most important facts or concepts are not always readily available, but hidden in the myriad of details that accompany them. To handle and digest the sheer amount of information we are exposed to in this information age, more sophisticated procedures are required to unveil the important parts of a text, and to allow us to process more information in less time. The goal of this project is to develop robust and accurate techniques to automatically extract important information from unstructured text, in the form of keyphrases (keyphrase extraction) or entire sentences (extractive summarization).
Funded by Google
[edit]
Open source graph visualization software. Takes descriptions of graphs in a simple text language, makes diagrams formatted as images, SVG for web, PS for PDF, GXL (XML dialect), and more.
TIR 2010
7th International Workshop on Text-based Information Retrieval
in conjunction with DEXA 2010
University of Deusto
Bilbao, Spain
30 August - 3 September 2010
S. Riedel, L. Yao, und A. McCallum. Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III, Seite 148--163. Berlin, Heidelberg, Springer-Verlag, (2010)