Virtual Biodiversity ViBRANT Literature Mining and Mark-up ViBRANT’s text processing tools David Morse, The Open University, UK, Dauvit King, The Open University, UK, ViBRANT/BeBOL/JEMU workshop, RBINS, 11 June 2013 ViBRANT Virtual Biodiversity
ViBRANT 2 of Literature Mining 14 ViBRANT is for taxonomists, so we look for: Taxon names Authors Locations Also interested in: Citations Relationships Mining for Names and Concepts
Virtual Biodiversity ViBRANT Literature Mining – harder than you think M BRITISH MUSEUM (NATURAL HiSi 26JU PRESENTED GENERAL UC.-lARY Bulletin ofthe BritishMuseum (Natural History) The ichneumon-fly genus Banchus in the OldWorld (Hymenoptera) M. G. Fitton series Entomology Vol51 Nol 25 July of14
Virtual Biodiversity ViBRANT 4 of GoldenGATE 14 Sautter, G., Agosti, D., and Böhm. K. (2007) Semi-Automated XML Markup of Biosystematics Legacy Literature with the GoldenGATE Editor. In Proceedings of PSB 2007, Wailea, HI, USA, 2007 Downloadable from online/proceedings/psb07/sautter.pdf online/proceedings/psb07/sautter.pdf
Virtual Biodiversity ViBRANT 5 of GoldenGATE 14
Virtual Biodiversity ViBRANT 6 of GoldenGATE in OBOE 14
Virtual Biodiversity ViBRANT 7 of GoldenGATE in OBOE 14
Virtual Biodiversity ViBRANT 8 of GoldenGATE in OBOE 14
Virtual Biodiversity ViBRANT 9 of GoldenGATE in OBOE 14
Virtual Biodiversity ViBRANT 10 of Visualising mark up 14
Virtual Biodiversity ViBRANT 11 of Taxonomic XML schemas 14 Lyubomir Penev, Christopher Lyal, Anna Weitzman, David Morse, David King, Guido Sautter, Teodor Georgiev, Robert Morris, Terry Catapano, and Donat Agosti. (2011) XML schemas and mark-up practices of taxonomic literature. ZooKeys 150: Downloadable from
Virtual Biodiversity ViBRANT 12 of Linked Open Data 14
Virtual Biodiversity ViBRANT 13 of Other tools 14 KEA Keyphrase Extraction Algorithm GNRD Global Names Recognition and Discovery Linnaeus Used for molecular data
Virtual Biodiversity ViBRANT 14 of Conclusion 14 Developing Literature Mining services deployed through OBOE. Initially aimed at ViBRANT’s core audience. Setting up workflow integrated with Scratchpads. Yet still permitting large, slow jobs.