|iConference2013: Workshop -- Help iDigBio Reveal Hidden Data: iDigBio Augmenting OCR Working Group Needs You (#CNFWSP11)
|Year of Conference
|Paul, Deborah L., P. Heidorn Bryan, Best Jason, Gilbert Edward, Neill Amanda, Nelson Gil, and Ulate William
|aocr, EF-1115210, iConference2013, iDigBio hackathon, information analysis, information organization, information retrieval, information services, iSchools, machine language, Natural Language, OCR, qualitative data analysis, research methods
|Integrated Digitized Biodiversity Collections, iDigBio, is an initiative funded under the National Science Foundation's (NSF) Advancing Digitization of Biological Collections (ADBC) program set up to help natural history museums get specimen data for hundreds of millions of specimens out of drawers, off of labels, out of field notebooks, out of old publications and into integrated databases for everyone's use. The iDigBio Augmenting OCR Working Group needs your wisdom, knowledge and collaboration as part of our multi-faceted approach to improve OCR strategies and natural language processing (NLP) algorithms used in digitization. Our workshop panelists, members of our working group, are eager to introduce the iSchools community to our challenges and get your input in our break-out sessions. Our research areas of interest include: image segmentation, autocorrection of typographical errors, semantic autocorrection, autonormalization, automated text segmentation, generating consensus records and user interfaces for these tasks. We seek your insights, collective experiences and partnership in order to find ways to improve the digitization process to create a national searchable online specimen-based data set that is fit-for-use by scientists and the public. Some ideas generated in this session may be implemented at the iDigBio hackathon being held at the Botanical Research Institute of Texas (BRIT) during the iConference.