Two ICS researchers, Google Summer of Code mentors for third consecutive year
Inés Olza and Cristóbal Pagán are part of the international consortium network Hen Lab, an institution participating in the global program.
PHOTO: Manuel Castells
Inés Olza and Cristóbal Pagán, researchers of the Institute for Culture and Society (ICS) of the University of Navarra, have participated this summer, for the third consecutive year, in the Google Summer of Code (GSoC). They have contributed as mentors of the international consortium network Hen Lab for the Study of Multimodal Communication, which brings together experts from more than 15 universities from different countries such as USA, Spain, Germany, Brazil or Norway.
Google Summer of Code is a global program that awards grants to young computer scientists from around the world to collaborate with institutions, groups at research and companies dedicated to developing code for open source tools. This year GSoC awarded 10 scholarships to international coders for network Hen projects, seven more than in the first year.
The network Hen Lab projects consist of developing automatic text (natural language processing), sound and image processing tools that can be incorporated into its Library Services International NewsScape for Television News.
In 2015, the approach of the GSoC-network Hen grants was audio analysis, while in 2016 the project focused on machine learning within the field of computer vision. The 2017goal has been to create a multimodal processing system to extract information about human communicative behavior from text, audio and video.
NewsScape is a gigantic corpus of spoken language, making it possible to study all multimodal aspects (gesture, prosody, images and sounds accompanying speech, television production effects, etc.). It is therefore an unprecedented tool that could revolutionize the study of speech and news coverage.
It currently contains some 340,000 hours of television news in English, Spanish and other European languages that can be searched automatically. NewsScape allows, for example, to compare the treatment of a topic on different channels and programs by searching for words core topic in their subtitles.
With respect to the Spanish news collection, it currently constitutes an unprecedented resource for the study of spoken Spanish, with some 6,000 hours of television and some 40 million synchronized subtitles.
