DeepText: Intelligent Text Analysis with Deep Learning
At a glance
- Project leader : Dr. Mark Cieliebak
- Deputy of project leader : Jan Milan Deriu
- Project team : Dominic Egger, Dr. Thilo Stadelmann
- Project budget : CHF 520'000
- Project status : completed
- Funding partner : CTI
- Project partner : World Vision , Universität Basel / Universitätsbibliothek Basel / Schweizerisches Wirtschaftsarchiv, Supertext AG, SpinningBytes AG
- Contact person : Jan Milan Deriu
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.
Publications
-
Deriu, Jan Milan; Lucchi, Aurelien; De Luca, Valeria; Severyn, Aliaksei; Müller, Simone; Cieliebak, Mark; Hofmann, Thomas; Jaggi, Martin,
2017.
Leveraging large amounts of weakly supervised data for multi-language sentiment classification [paper].
In:
Proceedings of the 26th International Conference on World Wide Web.
26th International World Wide Web Conference Committee (IW3C2), Perth, Australia, 3-7 April 2017.
Association for Computing Machinery.
pp. 1045-1052.
Available from: https://doi.org/10.1145/3038912.3052611
-
Deriu, Jan Milan; Cieliebak, Mark,
2017.
In:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017).
SemEval 2017 - International Workshop on Semantic Evaluation, Vancouver, Canada, 3-4 August 2017.
Association for Computational Linguistics.
pp. 334-338.
Available from: https://doi.org/10.18653/v1/S17-2054