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.
Read latest blog posts from SUMMA, click to read more.
The SUMMA user day, held on 3rd July 2017 at BBC Monitoring in Caversham, turned out to be a big success. Representatives from over 30 external media organizations, media access companies, government and research laboratories, and the like took part in the user day. After an introduction by coordinator Steve Renals from the University…
SUMMA will be actively contributing to the 6th Language Technology Industry Summit (LTInnovate 2017) in Brussels from 9-11 October. The session will have a panel discussion with representatives from Deutsche Welle, the BBC, LETA and the University of Edinburgh. The different technologies applied in the SUMMA project, its anticipated use for the broadcasting world, in…
SUMMA is organising its first user day to show off its platform and discuss potential use. The workshop will demonstrate our media monitoring platform and present the challenges and the solutions provided by the underlying technologies. The objective is to engage with people from industry who might be interested in SUMMA technologies and gather feedback from…
On April 3, a press release was issued announcing SUMMA presenting the first prototype of its multi-lingual media monitoring platform on 6 April 2017 at the 2017 Conference of the European Chapter of the Association for Computational Linguistics (EACL-2017) in Valencia, Spain. It will be shown that the platform uses cutting-edge Natural Language Processing…
During a meeting from the European branch of MESA (Media & Entertainment Services Alliance) and HITS (Hollywood IT Industry) in London, the SUMMA team organised a session on language technologies applied to videos for broadcast or film. Pressing topics in on localisation are addressed: Are the technologies useful for processing broadcast content and movies? Is…
Several SUMMA team members attended the BBC News Labs Hackaton on text-to-speech technologies (#newsHACK – Transcriptor) in London on 31 January and 1 February 2017. As shown in the picture below, the SUMMA team comprised of two members of user partner Deutsche Welle, i.e. Andy Giefer and Peggy van der Kreeft, and Renars Liepins from…
Peggy van der Kreeft from Deutsche Welle Innovation will represent SUMMA at an HLT (Human Language Technologies) workshop at the European Parliament in Brussels on 10 January 2017. The workshop, entitled “Language equality in the digital age towards a Human Language Project”, will contribute to put HLT on the European political agenda. SUMMA interests –…
Peggy van der Kreeft, from Deutsche Welle Innovation, represented SUMMA at the Media Fast Forward (MFF2016) event, organized by the VRT (Flemish Radio and Television company) in Brussels on 8 December 2016. Dieter Boen, VRT Innovation Manager, introduced the event and talked about VRT efforts on innovation collaboration and its tools, such as VRT Sandbox,…
Over the last two years, there has been a leap forward in machine translation research as deep learning methods, or neural networks, have been applied to translation. In September Google published a widely reported paper which claimed that for some types of content, neural machine translation (NMT) models were reaching human levels of performance. This…
