SUMMA integrates stream-based media processing tools (including speech recognition and machine translation) with deep language understanding capabilities (including named entity relation extraction and semantic parsing), for open-source applications and implemented in use cases at the BBC and Deutsche Welle.

SUMMA is a Horizon 2020 Research and Innovation Action, running from 1st February 2016 to 31st January 2019.

Latest Blog Posts

Read latest blog posts from SUMMA, click to read more.

Flexibility Through SUMMA User Interfaces

From the beginning, the SUMMA consortium decided to build a common monitoring platform which is robust and flexible. Thus, initially, also one common user interface was projected. As the project progressed, though, we developed several UIs to cater for a variety of target groups, interests and use cases. The initial, simplified SUMMA UI:  The advantage…

Deutsche Welle Users Explore Internal Monitoring

Internal monitoring is seen as keeping track of what is produced within one’s own organisation. Thus, in the case of Deutsche Welle, who focused on internal monitoring in SUMMA, this comes down to tracking what content was published across the different languages covered by Deutsche Welle (DW produces in 30 languages in total). SUMMA can…

Announcing End of SUMMA project

It’s done ! The SUMMA project ended officially on 31 January 2019. But it does not mean we stop here. The outcome is very promising, the tools will lead their own lives, and we will continue to inform and support the SUMMA community. We give you a brief overview of the results and achievements of…

Deutsche Welle Slackbot prototype

Deutsche Welle developed a slackbot as a tool for journalists during the SUMMA hackathon in London on 21-22 November 2017. The slackbot is an alert system as well as a research tool. Through the bot, journalists can explore Deutsche Welle content in various languages. It uses machine translation, summarization and clustering modules of SUMMA. In…

Deutsche Welle Data Dashboard

In the scope of SUMMA project, Deutsche Welle developed a data journalism dashboard. The dashboard has two components; trending entities for the last 24 hours and trending storylines since last month. The output from the SUMMA system is consumed by the dashboard through SUMMA APIs. Trending Entities Entities are people, places and organizations detected in the…

SUMMA Release as Open Source

A major achievement: SUMMA has released a first open-source version of the platform on Github! The platform has been presented at many events and has triggered a lot of interest. We received numerous requests on how to try it out, how to get access to the platform. Of course, we wanted to deliver it in…

SUMMA in a Nutshell

The SUMMA video is ready and released ! It explains in a nutshell how the SUMMA platform can help professionals working in the journalistic area benefit from the system using it for searching for trending topics in any language available in the platform (currently 9, but it can be expanded to most languages). It shows the…

SUMMA checked out by Berlin Film Studies academic researchers

The Deutsche Welle Innovation Team was invited to speak at the Berlin Free University for a group of mostly academic researchers focusing on film studies and technologies on 7 November. The theme of the 2-day AdA workshop was “Corpus Analysis of Time-Based Arts & Media”. The focus was enriching large data repositories through AV analysis.…

SUMMA hackathon in Bonn

The second SUMMA hackathon took place on 9 and 10 October in Bonn, Germany, attracting around 40 attendees from around Europe. Since the first hack, the organisers were aware that the focus of events such as these was gradually moving away from the competitive aspect of producing the best submission in a particular category, and…

Loading blog posts...