IPTC EXTRA - Open Source Rules Classification
Download as PPTX, PDF1 like887 views
The document discusses the 'extra' project developed by IPTC, funded by Google's Digital News Initiative with a total grant of €50,000. The project focuses on rules-based classification of news content, utilizing open source software and multilingual rules for news classification. A workshop is scheduled to finalize technical use cases and communications plans, with the next meeting planned for October 2016 in Berlin.
IPTC EXTRA - Open Source Rules Classification
- 1. “Extra” by Jeremy Brooks https://flic.kr/p/4aKH3c
- 2. EXTRA Stuart Myles * Associated Press * 14th June 2016 © 2016 IPTC (www.iptc.org) All rights reserved https://flic.kr/p/tgYcsA
- 3. EXTRA EXTraction Rules Apparatus • Rules-based classification of text • Open source software • EXTRA is being developed by the IPTC • Grant from the Digital News Initiative https://iptc.github.io/extra/ © 2016 IPTC (www.iptc.org) All rights reserved 3
- 4. Google DNI • Google’s €150 million Digital News Initiative fund – Stimulate innovation among European news organizations – https://www.digitalnewsinitiative.com/fund/ • Multiple funding rounds – First funding of €27 million to projects in 23 countries – http://googlepolicyeurope.blogspot.gr/2016/02/digital-news-initiative- first-funding_24.html • IPTC’s EXTRA project funded in first round - October 2015 – Developer €35,000 – Linguist €10,000 – Project Manager €5,000 – Total grant to IPTC from DNI = €50,000 © 2016 IPTC (www.iptc.org) All rights reserved
- 5. EXTRA EXTraction Rules Apparatus • Open source – IPTC always uses open licenses • Rules-based – Better for breaking news than statistical methods – More consistent and scalable than hand tagging – Easier to explain why rules classify content • Multilingual – Developing rules for two IPTC Media Topics Languages • News classification – Rules will be developed using news content corpora © 2016 IPTC (www.iptc.org) All rights reserved 5
- 6. EXTRA Progress Technical use cases https://docs.google.com/document/d/1O8pmFlohcGXThzyrWil_OFbDyqJk1Hcjpml_RRXu w6U/edit?usp=sharing Rules language requirements https://docs.google.com/document/d/1MMv5qlrLF71bBN1w1ErXaSyTKB2Kd1ksgixBnUO w0fQ/edit?usp=sharing Delivered roadmap to DNI Securing news corpora in two Media Topics languages – English from Thomson Reuters – German from APA – French from AFP © 2016 IPTC (www.iptc.org) All rights reserved 6
- 7. Communications plan – Working on EXTRA – but who might not make every meeting – IPTC membership who are interested in EXTRA – Beyond IPTC who are interested / might want to work on EXTRA – Teleconferences https://iptc.org/events/ – Email https://groups.yahoo.com/neo/groups/iptc-extra/info – Documentation • http://dev.iptc.org/Topic-EXTRA • https://iptc.github.io/extra/ • Do we need – Team communications - Slack? – Outreach - Twitter? Blog? Medium? LinkedIn? © 2016 IPTC (www.iptc.org) All rights reserved 7
- 8. EXTRA Wednesday Workshop • Review technical use cases • Review rules language requirements • Select licenses – Source code – Corpora • Decide on communications plan • A plan for a plan – Technical foundations – Select consultants © 2016 IPTC (www.iptc.org) All rights reserved 8
- 9. Date and Place of Next Meeting Berlin, Germany 24 – 26 October 2016 https://flic.kr/p/dzWJB Tack och adjö! © 2016 IPTC (www.iptc.org) All rights reserved 9