World Usability Day 2017 Berlin | Bright Light in the Data Fog – Exploration of Large Document Corpora

Bright Light in the Data Fog – Exploration of Large Document Corpora

Today’s business communication documents almost everything about an organisation’s internal affairs as well as their cooperation with others through emails, contracts, protocols, and more. Establishing an overview of such a corpus is almost impossible due to the sheer quantity and diversity of all the unstructured documents. After major leaks like the Panama Papers, journalists want to quickly gain insights about who involved in what with whom and when. Deep Learning and Text Mining enables computers to process large amounts of data to identify salient phrases, topics, entities, and their relationships. Making this extracted information accessible through interactive visualisations is a major challenge. In this workshop, we want to invite the community of usability professionals to discuss some of the challenges with us and develop new creative approaches, so that we can provide journalists a bright light to guide their way through the fog of data.

Ort & Zeit

Event Hours(1)

  • MOA 1/2

    11.00 – 12.30

    Tim Repke
    Hasso-Plattner-Institut (HPI)

Speaker

Tim Repke

Tim Repke studied Computer Science at Humboldt University and Swansea University. As a PhD student at the Hasso-Plattner-Institute, he develops methods that help gaining insights from large and diverse collections of documents by making the inherent knowledge explorable. Working in a London-based startup, he found his interest in information extraction and unstructured data, which lead to the topic of his master’s thesis on citation data extraction from arbitrary webpages.

Firma: Hasso-Plattner-Institut (HPI)