DeepText: Intelligent Text Analysis with Deep Learning
Description
DeepText develops a software framework to automatically analyse texts in order to extract important information. The framework comprises modern algorithms from the field of machine learning (deep learning) that are better at analyzing texts than traditional approaches. They can for example be used to extract important topics or named entities like company or person names from a text.
Key Data
Projectlead
Deputy Projectlead
Project team
Dominic Egger, Prof. Dr. Thilo Stadelmann
Project partners
World Vision; Universität Basel / Universitätsbibliothek Basel; Supertext AG; SpinningBytes AG
Project status
completed, 09/2016 - 02/2018
Funding partner
CTI
Project budget
520'000 CHF
Publications
-
Leveraging large amounts of weakly supervised data for multi-language sentiment classification
2017 Deriu, Jan Milan; Lucchi, Aurelien; De Luca, Valeria; Severyn, Aliaksei; Müller, Simone; Cieliebak, Mark; Hofmann, Thomas; Jaggi, Martin
-
SwissAlps at SemEval-2017 Task 3 : attention-based convolutional neural network for community question answering
2017 Deriu, Jan Milan; Cieliebak, Mark