@inproceedings{MuellerGhoshReyetal.2022, author = {Mark-Christoph M{\"u}ller and Sucheta Ghosh and Maja Rey and Ulrike Wittig and Wolfgang M{\"u}ller and Michael Strube}, title = {Reconstructing manual information extraction with DB-to-document backprojection: Experiments in the life science domain}, series = {Proceedings of the First Workshop on Scholarly Document Processing. Online, November 19, 2020}, editor = {Muthu Kumar Chandrasekaran and Anita de Waard and Guy Feigenblat and Dayne Freitag and Tirthankar Ghosal and Eduard Hovy and Petr Knoth and David Konopnicki and Philipp Mayr and Robert M. Patton and Michal Shmueli-Scheuer}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, Pennsylvania}, issn = {978-1-952148-70-5}, doi = {10.18653/v1/2020.sdp-1.9}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-110854}, pages = {81 -- 90}, year = {2022}, abstract = {We introduce a novel scientific document processing task for making previously inaccessible information in printed paper documents available to automatic processing. We describe our data set of scanned documents and data records from the biological database SABIO-RK, provide a definition of the task, and report findings from preliminary experiments. Rigorous evaluation proved challenging due to lack of gold-standard data and a difficult notion of correctness. Qualitative inspection of results, however, showed the feasibility and usefulness of the task.}, language = {en} }