Challenges in Extracting and Managing References
Download as PPTX, PDF0 likes822 views
The 'Excite Workshop 2017' focused on improving citation data extraction and management in the social sciences, addressing the current shortage of citation data. Key objectives included developing tools for reference extraction and establishing an API for third-party access to citation data. The workshop featured discussions on various extraction techniques, a status report on the Excite project, and hands-on sessions to engage participants.
Challenges in Extracting and Managing References
- 1. “Challenges in Extracting and Managing References” EXCITE Workshop 2017 Philipp Mayr GESIS – Leibniz Institute for the Social Sciences 2017-03-30 http://west.uni-koblenz.de/en/research/excite/workshop-2017 #excitews2017
- 2. Who we are • PI: Steffen Staab (WeST), Philipp Mayr (GESIS) • Researchers: Behnam Ghavimi, Martin Körner • Collaborator: Heinrich Hartmann (Independent) 2
- 3. EXCITE: Background 3 • We run productive search systems and research in information retrieval, recommendation systems and knowledge discovery Sowiport http://sowiport.gesis.org/ Related-work http://dev.related-work.net/ • Shortage of citation data for the international and German social sciences • Open availability of citation data is still very limited Open Citation Corpus http://opencitations.net/ CitEc: Citations in Economics http://citec.repec.org/
- 5. EXCITE: Main objectives • Narrow the supply gap of citation data in the social sciences • Improve the breadth and accuracy of current reference extraction systems • Develop web service API to allow third-parties to extract citation data from arbitrary publications • Integrate and publish the extracted citation data General objectives • Developing a toolchain of citation extraction and matching software • Tools and data will be made available to researchers 5
- 6. EXCITE: five steps (1) extraction of text from source documents, (2) identification of reference sections and other forms of embedded reference information within the text, (3) segmentation of individual references into its constituent fields such as author, title, etc., (4) matching of reference strings against databases of bibliographic information, (5) the export of matched references to reusable formats 6 1st workshop
- 7. EXCITE: Outcomes • Open reference extraction tools for PDF documents • Open datasets of segmented references • Web service API for citation extraction • Assessment of the overall quality of the extraction and matching pipeline • Open gold standard testbed • Improved infrastructures and services 7
- 8. Workshop Agenda: Day 1 8 12:20 Information Extraction out of Born-Digital Scientific Articles Roman Kern, TU Graz 12:40 Advanced citation matching and large-scale full-text analysis Nees Jan van Eck, Leiden U 13:00 Lunch Break (Cafeteria) 14:20 APIs for third parties to extract and deposit output executions of automated extraction pipelines (via videoconferencing) Min-Yen Kan, NU Singapore 14:40 Extracting references from scientific articles in CERMINE system Dominika Tkaczyk, U Warsaw 15:00 Coffee Break (Cafeteria) 15:30 CitEc to CitEcCyr. A stab at distributed citation systems. (via videoconferencing) Thomas Krichel, Open Library Society, NYC 15:50 EXCITE project: Status report Behnam Ghavimi, GESIS Martin Körner, WeST Heinrich Hartmann, Circonus 16:10 Processing of in-text References: Towards a Semantic Analysis Marc Bertin, U Toulouse 16:30 Citations in Utopia Documents David Thorne, U Manchester 16:50 Coffee Break (Cafeteria) 17:20 Research around the Tagging System BibSonomy Andreas Hotho, U Würzburg 17:50 LOC-DB: A Linked Open Citation Database provided by Libraries. Motivation and Challenges. Kai Eckert, HDM Stuttgart Anne Lauscher, HDM Stuttgart Akansha Bhardwaj, DFKI 18:20 tbd (via videoconferencing) Lee Giles, Penn State U
- 9. Workshop Agenda: Day 2 • Hand-on sessions 9 9:00 Second Day Kickoff (Room: West II) 9:15 Extraction Result Discussion Group Gold Standard Discussion Group Collaboration Discussion Group 11:15 Coffee Break (Cafeteria) 11:30 Extraction Result Discussion Group Gold Standard Discussion Group Collaboration Discussion Group 12:30 Closing Talks (Room: West II) 13:00 End
- 10. Thank you Contact: Dr Philipp Mayr GESIS - Leibniz Institute for the Social Sciences, Germany Email: philipp.mayr@gesis.org Twitter: @philipp_mayr • Workshop website http://west.uni-koblenz.de/en/research/excite/workshop- 2017 • GIT https://github.com/exciteproject/ 10