SENSEI

Conversational interaction is the most natural and persistent paradigm for business relations with customers. In contact centres millions of calls are handled daily. On social media platforms millions of blog posts are exchanged amongst users. Can we make sense of such conversations and help create assets and value for private and public organisations’ decision makers? And indeed for anyone interested in conversational content?

Project aims

The SENSEI Project was a 3-year EU-FP7 funded project (2013-2016), which aimed to develop summarisation/analytics technology to help users make sense of human conversation streams from diverse media channels.

The project also aimed to design and evaluate its summarisation technology in real-world environments, to improve task performance and productivity of end-users.

You can read more about the project in this Guardian article.

Objectives and outcomes

SENSEI’s scientific and technological objectives are to develop new technologies that will empower users to make sense of conversations through the following advances:

• Parse human conversations for both content, affect and other behavioural traits.

• Create adaptive technology to address the diversity and velocity of the media sources.

• Automatically generate human-readable multimedia, graphical and tabular summaries of dialogues and/or multiparty conversations.

• Evaluate technology where it is being used and not only in the lab. We will engage end- users ranging from language data analysts to quality assurance professionals and news media analysts in real task settings.