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.

Elasticsearch Percolator

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 office@iptc.org