By Jennifer Parrucci
In leading the way for the creation of a rule-based, multilingual classification system, the IPTC’s EXTRA (EXTraction Rules Apparatus) project is providing a powerful and innovative way for publishers to classify documents using the industry standard IPTC Media Topics taxonomy, as well as tailor rules to their own existing taxonomies. By making these powerful capabilities freely available to the global news publishing community, the EXTRA project catalyzes a variety of innovative outcomes including intelligent aggregation, search and analytics.
In 2016, the IPTC received a €50,000 grant from Google’s Digital News Initiative to create EXTRA , an open source, rules-based, classification system for the annotation of news documents with high-quality subject tags that can be used by publishers to deliver valuable services including, but not limited to, subject related content streams and collections, advertising targeting and content recommendations.
While EXTRA is still in development, attendees of the IPTC Spring Meeting in London were treated to an update and EXTRA demo. The group was shown the rule writer tools and interface and given an example of how to write and test rules. Feedback on these tools is welcomed – the EXTRA project is available via github, including the Extra User Manual, the Extra core code and the Extra API and UI.
A Rules-Based System Improves Tag Consistency Over Other Methods
The fact that EXTRA is rules-based, rather than relying on hand-tagging or statistics-based machine learning systems on the other, is key. EXTRA’s rules-based system allows publishers to improve tag consistency over hand-tagging methods, and provides much more rapid and scalable functionality. EXTRA also allows publishers to adapt their tagging for breaking new and low-frequency topics that cannot be captured by statistical approaches that require numerous annotated results. Users of EXTRA can tweak and customize the extraction rules to suit the needs and patterns of their publication and will be able to either use the IPTC Media Topics as the basic vocabulary or load their own taxonomies into the software. And unlike machine learning, which is a “black box,” EXTRA makes it easier to explain why a given classification was used, and to precisely explain–and correct–mistakes.
A team of IPTC members began by creating a technical requirements document for the project. System requirements included that the tool could be easily configured by given taxonomy, corpora and rules schema, that a comprehensive query language for rules creation was decided upon, that document classification resulted in high precision and recall scores, that the classification could be done in multiple languages, that the system and UI were intuitive and transparent and that everything be available through an open MIT license.
After an extensive search, IPTC hired Infalia in January 2017 to develop the software for EXTRA. Two linguists, one for German and one for English, were hired to create sample rules based on the IPTC Media Topics. The Austrian Press Agency (APA) and Reuters licensed corpora to be used for the EXTRA development process and as examples for users. The working version of EXTRA was completed at the end of June 2017.
Demo of EXTRA: Taxonomy Management Feature
On May 16, 2017 attendees of the IPTC Spring Meeting in London were treated to an EXTRA demo and update about the project. During the demo, the group was shown the rule writer tools and interface and given an example of how to write and test rules.
The group was first shown the taxonomy management feature. For the demo, we pre-loaded the taxonomy management module with the IPTC Media Topics in both English and German. Users are free to use whatever taxonomies they would like. If a taxonomy is selected, one will be able to see the terms in that taxonomy along with their term definitions. The user will also be able to edit and delete terms from that taxonomy.
To assist the linguists in writing rules, they used the document search to see what articles within the corpora returned for each Media Topic. This process provided insights into keywords, phrases and article structures that could alert the engine that an article was about a particular topic, and enabled refinement of the rules or the vocabularies. Users can see the IPTC NewsML-G2 XML of a selected document to see what fields they might want to leverage in the rule.
It was then time to show some sample rules. The EXTRA Query Language enables rule writers to create rules that analyze the text of the documents using ElasticSearch operators plus some custom ones. It allows for stemming by language, querying by a whole document or tokenized by a sentence, paragraph or headline. Rules can be written to target the proximity of words or phrases from each other, whether in the document as a whole or a specific field, the frequency of words or phrases individually or how many words from a list appear.
Examples of simple rules:
A rule that requires that “play” and “bass drum guitar piano” appear in proximity of 3 words
(text_content any/stemming “play”)
(text_content any/stemming “bass drum guitar piano”)
A rule that requires that “Merkel” and “Obama” appear in the same paragraph
(body = “Merkel”)
(body = “Obama”)
After writing a rule, the user has the ability to syntax check their work.
Then, one can run the rule against a corpus to see how many articles match the rule and were tagged with that term (if it is a pre-existing tag), how many many articles only matched the rule and how many articles matched the rule and not the tag. The user is also shown precision and recall scores. All of this data allows the user to tweak their rule until they are happy with the result.
While EXTRA was still in development at the time of the EXTRA demo, the response from the room was positive and members were eager for the finished product.
Feedback on EXTRA:
Please send your feedback about EXTRA to email@example.com.
Jennifer Parrucci is a the group lead for IPTC’s News Codes Working Group and a Senior Taxonomist for NYTimes.com.
A ODRL (Open Rights Digital Language) Candidate Recommendation was released by W3C’s Permissions & Obligations Expressions (POE) Working Group on 26 September: ODRL has been updated to a generic information model that can be customized by any industry or business sector. IPTC is looking for members and experts with experience in defining licensing information in a machine-readable way to help adapt IPTC’s RightsML standard according to the new ODRL Recommendation, which will specifically address the needs of the news industry.
IPTC’s RightsML – https://iptc.org/standards/rightsml/ – is a standard providing a data model for marking up rights expressions about content of all relevant media types in a machine-readable way. The standard was introduced in 2012 and from the start it was built on ODRL – Open Digital Rights Language – a rights expression framework defined outside IPTC. At that time, a W3C Community Group was backing ODRL.
In early 2016 W3C established a formal Permissions & Obligations Expressions (POE) Working Group – https://www.w3.org/2016/poe/charter – to make a W3C Recommendation from the Community Group specifications, and on 26 September a Candidate Recommendation was released. The work on that W3C Recommendation will be closed by the end of 2017, and IPTC will take action to align a next RightsML version with the Recommendation.
IPTC Action: Update RightsML by Synchronising It With the New W3C Recommendation as ODRL RightsML Profile
The transfer of ODRL from a Community Group to a Recommendation approved by the W3C Consortium was not only a copy and paste action. The basic design has not been changed but the status of many actions, constraints or party functions has been changed from “normative” to “non-normative.” The reason was to make the ODRL Recommendation a generic information model which can be easily adapted to the different needs of various business sectors. This has been demonstrated by the range of participants of the W3C Working Group covering needs and interests from media companies and their trade associations, financial data providers, and universities.
The solution for that is called ODRL Profile: it defines all the actions, kinds of constraints, types of involved parties and more which are typical to a business sector and these definitions are add-ons to the basic Information Model of the Recommendation. This also slims down the specifications: businesses behind media assets don’t have to take care of the requirements regarding e.g. scientific papers.
IPTC has taken the role of defining the RightsML Profile of ODRL covering the needs of the news industry. Writing down the definitions fitting into the context of ODRL will not be that hard. Michael Steidl and Stuart Myles of the IPTC are invited experts of the ODRL/POE Working Group and have been active in its development from the start.
The big challenge is to determine which business needs of the news industry should be covered by the actions, constraints or parties defined by the RightsML Profile. To achieve that we need people from IPTC members and experts from other companies who have any experience in defining licensing information in a machine-readable way. Regular conference calls will take place from October 2017 to early 2018 to select and define what should be included to update RightsML Profile.
ODRL: From Candidate Recommendation to the Final Recommendation
On 26 September 2017, W3C published the Candidate Recommendation of ODRL. Links to the relevant W3C documents and other relevant resources are provided in the Details section below.
This opens a test phase until mid-November; in this period the Information Model and Vocabulary documents should be reviewed and comments may be posted. Further, W3C procedures specify that the Information Model and Vocabulary should be implemented into software at least by two parties and be tested against a list of criteria. Any party interested in ODRL and all IPTC members are invited to take this action. For more information contact Michael Steidl (firstname.lastname@example.org).
Details for Creating the RightsML ODRL Profile:
- POE Working Group Charter: https://www.w3.org/2016/poe/charter
- POE Working Group home page: https://www.w3.org/2016/poe/wiki/Main_Page
- ODRL Information Model – Candidate Recommendation: https://www.w3.org/TR/2017/CR-odrl-model-20170926/
- ODRL Vocabulary – Candidate Recommendation: https://www.w3.org/TR/2017/CR-odrl-vocab-20170926/
- RightsML Profile outline: http://w3c.github.io/poe/rightsml/ (currently only the section heads are shown)
- The RightsML landing page of the IPTC website: https://iptc.org/standards/rightsml/
- The current RightsML on the IPTC Developer Site: http://dev.iptc.org/RightsML
- The current and small RightsML specification document: http://www.iptc.org/std/RightsML/1.1/RightsML_1.1EP2-spec_1.pdf
- IPTC contact: Michael Steidl – email@example.com
IPTC’s Board of directors and Michael Steidl jointly announce that Michael will retire from employed work in mid-2018 and he will step down as IPTC’s Managing Director by then.
The Board has already started to make plans for selecting a new IPTC Managing Director and will provide more details in a separate communication.
Chairman of the IPTC Board
Being IPTC’s Managing Director for 15 years is a great experience and I’m happy about having been involved in the development and roll-out of 9 new standards, the new Media Topic taxonomy and other vocabularies; further in setting up new formats of the face -to-face meetings and in the creation of new types of meetings. Being in contact with our membership is also part of the bright side of my IPTC life and I enjoyed spreading the word about IPTC and its work among people knowing only little or nothing about our organisation. It was great to welcome 74 new members in this period.
Unfortunately, even such a great period of life started to apply burden on me, so I’ve decided to retire from employed work next summer. Please look forward to what the future will bring.
Managing Director of IPTC
IPTC holds its Autumn Meeting this year in Barcelona, Spain, from Monday, 6 November, through Wednesday, 8 November.
A team of IPTC Leads is working on the topics of the Autumn Meeting and we have already a very exciting list:
- Discussion topic: The Art and Science of Practical Metadata
- Discussion topic: System Vendors and News Exchange
- Discussion topic: Automating News – Speed is nothing without Accuracy
- Discussion topic: Trust in the Media
- Discussion topic: JSON – Man for all Seasons?
- Sessions of the NewsML-G2, ninjs, NewsCodes, Video/Photo Metadata and Rights Expression Working Groups; and of the Public Relations and the Standards Committee
- Annual General Meeting
By Sarah Saunders
Ten years ago, the very first IPTC Photo Metadata Conference in Florence was packed with photographers and picture libraries eager to discuss ways of protecting their work in the digital environment. The image industry has expanded enormously since. The image industry has the additional challenge of vast numbers of images crowding the web, and the difficulty of finding the relevant picture, as well as the metadata relating to it.
IPTC Photo Metadata Conference 2017 was designed to look into the future, with a focus on image search using AI or Artificial Intelligence. The ability of computer systems to learn from humans has increased enormously in recent years, and the necessary computer power has now become available. The question for the conference was – how far can these systems help the professional image industry sharpen up its search capability and make gains in productivity?
Solution for Auto Tagging in the Image Industry
Kai-Uwe Barthel, professor of visual computing at HTW Berlin University gave a clear exposition on the history of the field and of the pressing need to create solutions for the picture industry. There are now too many images for classical search systems to handle, but using Neural Network Analysis – a variant of AI – computer systems can be taught to tag and recognise images in a fraction of the time it takes to manually tag. As most online images are untagged, a combination of human tagging and visual similarity search presents a viable way forward. But Barthel and his team have also researched new methods of presenting images, using three dimensional structures to dig into results with large numbers of images visible at one time.
Speakers on the use of AI came from across the industry, presenting solutions which can be put into practice now. The key to success in this area is to have enough content for the computers to learn from, and this can be achieved in a number of different ways. General AI systems produce good results for skies and beaches and general themes because they’ve had the data to learn from. But users can set a system to learn from their own content so that more specialist content can be tagged if the conditions are right. Computers are learning faster, and need fewer images to learn from than before.
AI systems can be trained to recognise faces, text, colours, composition, scenes, and objects, but can also be trained in the aesthetics of image selection, with one speaker maintaining that twenty images are enough to train a system in a particular brand aesthetic. But speakers admitted also that defining the precise location of what is shown in an image by its content was tested but it did not work in a reliable way.
Speakers stressed that the important element in computer learning is the understanding of the nature of the material to be tagged, an attribute which is currently not about to be taken over by artificial intelligence. The benefits in speed and productivity will be enormous but we’re not yet talking about doing away with human skills altogether!
IPTC Video Metadata and Easier Cross Media Distribution
The first afternoon session by IPTC Managing Director Michael Steidl was about the IPTC Video Metadata Hub (VMH), published in 2016 to provide a standard set of fields for use across the varied technologies used in video. Many of the Video Hub fields are equivalent to those in IPTC Photo Metadata Standard, which helps streamline cross media distribution. The VMH can be applied down to the level of video clips, which makes it a useful metadata tool for production, archive and distribution.
Technology That Protects Rights Information in Google Image Search
The IPTC conference was held a day after a CEPIC seminar on Google. The Google image search scrapes images from their original sites and displays them in its own environment. This is bad for rightsholders as images can be saved and downloaded direct from Google without reference to the original site. Picture libraries and agencies lose significant traffic to their sites as a result with a German agencies survey indicating a drop of 50 percent in traffic. The recent fine levied by the EU on Google for anti-competitiveness in comparative shopping sites is encouraging and has paved the way for scrutiny of Google’s actions with online images.
The second presentation of the afternoon presented a solution for the problems raised in the Google seminar. SmartFrame technology allows images to be presented online without the danger of being scraped by Google as this is disabled by technical means. Most of the mechanisms people use to download images – like right-click – are disabled too. Images can be shared as links so social media sharing doesn’t lead to an image becoming orphaned and lost in the websphere. And when an image is viewed as a thumbnail in Google, there is a clear indication that it is a copyrighted image, and a link back to the originating site. Rob Sewel, Pixelrights CEO demonstrated how product items within an image could be linked back to a brand website, providing ways of funding photography in the future where photography provides a link to a paid-for advertising service. The technology could be put to all sorts of uses in both commercial and non-commercial fields, and gives control back to creators and their agents.
The success of this kind of technology, as with all solutions to image grabbing and orphaned images, lies in the uptake of the technology. To be truly protective of copyright, client websites would need to implement a technology like SmartFrame.
The IPTC Photo Metadata Conference 2017 was fascinating from start to finish for the about 60 attendees on location, the level of presentations was extremely high, and the presentations and videos are all available on the website at https://iptc.org/events/photo-metadata-conference-2017/.
Sarah Saunders runs Electric Lane, an independent DAM consultancy specialising in workflow planning, asset retrieval, data management and DAM project management. She works with IPTC’s Photo Metadata Working Group.
IPTC named Bill Kasdorf, longtime publishing executive and VP and Principal Consultant at Apex Content and Media Solutions, as its new Public Relations Chairperson.
IPTC is a consortium of news agencies, publishers and industry vendors that develops and publishes technical specifications and standards to promote the easy, accurate and inexpensive sharing of news and information in all media. Kasdorf’s main goals as Marketing and Public Relations Chairperson are to increase and strengthen the membership of IPTC, and to extend awareness of IPTC’s work to other sectors of publishing beyond news that would benefit from IPTC’s work.
“Although the technical standards developed by IPTC are rooted in the news media sector, the work of IPTC is incredibly important and useful to all areas of publishing and media, as well as related fields such as library science and the cultural heritage sector,” Kasdorf said.
Kasdorf’s experience gives him a broad perspective across the major sectors of the publishing ecosystem – trade books, educational publishing, scholarly and scientific books and journals, magazines, and news. General editor of The Columbia Guide to Digital Publishing, he is active in many professional and standards organizations. He serves on the Steering Committee of the W3C Publishing Business Group and is a member of the W3C Publishing Working Group; he chairs the Content Structure Committee of the Book Industry Study Group; and he is active in the Society for Scholarly Publishing, of which he is a Past President. He serves on the editorial boards of Learned Publishing and the Journal of Electronic Publishing.
In his consulting practice, Kasdorf has served clients globally, including large international publishers such as Pearson, Wolters Kluwer, and Kaplan; scholarly presses such as Harvard, MIT, and Cambridge; aggregators such as VitalSource; and global organizations such as the World Bank, the British Library, and the European Union.
“The PR Chairperson should combine ideas from our membership with needs from up-to-date marketing strategies and Bill will do this in an excellent way” said Michael Steidl, Managing Director of IPTC.
“IPTC is at the forefront of the publishing ecosystem in the development and implementation of machine processable rights expressions, as well as photo and video metadata,” Kasdorf said. “We live in a multimedia world, and IPTC is providing essential technologies for making that world work.”
An updated version 2.25 of NewsML-G2 is available as Developer Release
- XML Schemas and the corresponding documentation are updated
- the Structure Matrix Excel sheet is updated
Packages of version 2.25 files can be downloaded:
- All XML Schemas plus Structure Matrix from https://www.iptc.org/std/NewsML-G2/NewsML-G2_2.25.zip
- The same without XML Schema documentation in HTML: https://www.iptc.org/std/NewsML-G2/NewsML-G2_2.25-noXMLdocu.zip
- New: in the newsml-g2 repository on GitHub: https://github.com/iptc/newsml-g2
All changes of version 2.25 can be found on that page: http://dev.iptc.org/G2-Approved-Changes
An important decision was taken: the Core Conformance Level will not be developed any further as all recent Change Requests were in fact aiming at features of the Power Conformance Level, changes of the Core Level were only a side effect.
The Core Conformance Level specifications of version 2.24 will stay available and valid, find them at http://dev.iptc.org/G2-Standards#CCLspecs
After 12 years of collaborative work on establishing and implementing photo metadata standards, IPTC, the global technical standards body of the news media and related industries, announced Adobe Systems Incorporated is joining as a Voting Member. Adobe’s membership was announced at IPTC’s Spring Meeting today in London.
“Adobe is a key player in the media production ecosystem, so we are thrilled to welcome them as a member of the IPTC,” said Stuart Myles, Chairman of the Board of IPTC, and Director of Information Management at Associated Press. “We look forward to working together with Adobe on driving continued improvements in the workflows of photo and video creators around the world.”
“Adobe has a long history of working informally with the IPTC, and we look forward to further success as we participate directly and contribute as a Voting Member,” said Dr. Scott Foshee, Principle Scientist, Adobe. “Our close involvement will not only enable greater coordination between Adobe and the IPTC, but will also allow Adobe to facilitate better coordination across the photography standardization community.”
Photo metadata is key to protecting images’ copyright and licensing information, and for managing digital assets. IPTC’s Photo Metadata Standard, created with contributions by Adobe, is the most widely used because of universal acceptance among photographers, distributors, news organisations, archivists, and developers. Adobe’s metadata management software, which supports the IPTC standard, is used by Adobe Photoshop, Lightroom, Illustrator, Acrobat, and Premiere.
“Adobe’s implementation has made IPTC photo metadata very popular,” added Michael Steidl, IPTC Managing Director. “For 12 years we have been collaborating on fostering professional use of IPTC photo metadata by photo businesses – building on our success by conducting research and incorporating feedback from users. This membership will open yet more opportunities for better tagging of photos and videos.”
Adobe first adopted IPTC IIM metadata in Photoshop around 1994 and later created the metadata format XMP. In 2004 IPTC and Adobe joined forces to support a consistent use of metadata: The first IPTC Photo Metadata Standard was created jointly. A main goal of the standard was to provide support for photographers and photo editors to use the fields in correct and consistent ways.
Adobe will be a Voting Member of IPTC, signifying Adobe as a key player and industry leader. IPTC currently has about 60 members. Its voting members take part in all decisions regarding IPTC standards. Delegates can participate in working parties and groups, may request changes, and make contributions to standards’ development.
News Classification Rules Being Developed for English and German with IPTC Media Topics
The IPTC has reached the first milestone in EXTRA, the Google/DNI project to build an open source rules engine for news. We are partnering with Infalia PC and have selected the Elasticsearch engine for developing a high-performance, rules-based news classifier. We are licensing an English language news corpus from Reuters and one in German from the Austrian Press Agency for use within the project. We have two linguists creating sample rules for classifying those corpora with IPTC’s Media Topics using the EXTRA engine. The project is on track to deliver a working version of the engine, together with the sample rules, by the summer of 2017.
EXTRA Open Source Rules for News
EXTRA (“EXTraction Rules Apparatus”) is an open source project to classify news text using rules. The engine allows news organizations to precisely identify the categories to which a piece of news belongs by specifying Boolean rules, with sophisticated natural language processing capabilities. Rule-based classification is better for breaking news than statistical methods, since it doesn’t require re-training using example news items (which typically take time to produce). Automated classification is generally more consistent and scalable than hand tagging of news. Most machine learning techniques are essentially “black boxes”, whereas rules provide much greater transparency – and therefore ability to control – why a piece of content is classified in a particular way. For all of these reasons, we believe that the EXTRA rules engine is ideally suited for news classification.
After evaluating a number of open source frameworks, we decided to make Elasticsearch’s percolator technology the foundation for the EXTRA engine. Our testing indicates that Elasticsearch supports indexing a large number of rules. The percolator has performant and scalable support for matching indexed rules against incoming documents, the core task of the EXTRA engine. Elasticsearch has an active open source community, as well as options for commercial support.
The EXTRA Requirements, Design, API and Rules Language
We have drawn up a detailed set of technical requirements and have created a high level technical architecture for EXTRA. We have designed the EXTRA API and the rule language. Linguists are working on writing the rules to classify English and German news using IPTC’s Media Topics taxonomy
IPTC, Infalia, Google DNI
EXTRA is being developed by the IPTC, an international consortium of news agencies, publishers and system vendors. The project is funded by the Digital News Initiative, Google’s €150 million fund aimed at stimulating innovation amongst European publishers. In 2016, IPTC applied for and won a DNI grant of €50,000 to develop the EXTRA engine. As a development partner, IPTC selected Infalia PC, a spin-out from the Information Technologies Institute of the Centre for Research and Technology Hellas with significant expertise in data analytics and natural language processing.
If you’d like to learn more about the IPTC or the EXTRA project, please contact firstname.lastname@example.org
IPTC’s Photo Metadata Working Group has released the Cultural Heritage Panel plugin for Adobe Bridge, which focuses on fields relevant for images of artwork and other physical objects, such as artifacts, historical monuments, and books and manuscripts.
Sarah Saunders and Greg Reser, experts from the cultural heritage sector, conceived the IPTC Cultural Heritage Panel to address needs of the photo business and growing community of museums, art foundations, libraries, and archive organisations. Furthermore the panel fills a gap: Many imaging software products, including Bridge, do not support all metadata fields of the IPTC Photo Metadata Standard 2016 for artwork or objects.
The artwork or object fields – a special set of metadata fields developed by IPTC a few years ago – describe artworks and objects portrayed in the image (for example, a painting by Leonardo da Vinci). This means that descriptive and rights information about artworks or objects is recorded separately from information about the digital image in which they are shown. Multiple layers of rights and attribution can be expressed – copyright in the photo may be owned by a photographer or museum, while the copyright in the painting is owned by an artist or estate.
The new plugin for Bridge (CC versions up to 2016 and CS6 were tested) allows people to view the image data, and write into these fields using a simple panel, which has been tailor-made for use in the heritage sector. The panel includes fields for artwork/object attributes and also relevant digital image rights.
“The Cultural Heritage Panel will be very useful for people working in the heritage sector in museums and archives,” Saunders, a consultant specialising in digital imaging and archiving. “It allows them to manage and monitor data about objects and artworks that is embedded in the IPTC XMP fields in the image.”
“The metadata can then be transferred into an organisation’s digital asset management system; the panel helps ease the ingest process,” Reser said.
Reser also noted that the panel helps incorporate more people into workflows, such as freelance photographers, who otherwise may not have access to an organisation’s digital asset management system. The Cultural Heritage Panel allows them to be an efficient part of the process of viewing the metadata included with an image, and adding to it when appropriate.
“IPTC is the most popular schema in embedded metadata,” Reser said. “Over time I bet we’ll see a lot of the cultural heritage fields creep into off-the-shelf programs and software.”
The panel is free, includes an easy-to-use interface, and includes key image administration fields. Image caption and keywords can be automatically generated from existing Artwork or Object data.
Download the IPTC Cultural Heritage Panel and User Guide for Adobe Bridge.