A Libraries & Big Data Brown Bag brought to you by the Information Science program at the MIT Libraries
Bring your lunch and join us for this fascinating presentation with Ophir Frieder, the Robert L. McDevitt, K.S.G., K.C.H.S. and Catherine H. McDevitt L.C.H.S. Chair in Computer Science and Information Processing at Georgetown University. This brown bag is appropriate for intermediate and advanced researchers and anyone interested in Big Data.
Many consider “searching” a solved problem, and for digital text processing, this belief is factually based. The problem is that many “real-world” search applications involve complex documents — comprising a mixture of images, text, signatures, tables, etc., and often available only in scanned hardcopy formats — and such applications are far from solved. Some of these documents are corrupted, some contain multiple languages, and accurate search systems for such document collections are currently unavailable.
This session will cover:
- Efforts at building a complex document information-processing prototype and previous complex document benchmark development efforts
- Spelling correction in adverse environments, including foreign name search and medical term search
- Analyzing social media, an additional, non-traditional search environment
Learn more about this presentation.
Lunch will be provided, but attendees should bring their own beverage.