The CRESS API is a multilclass CNN classifier that is trained on the CrisisLexT26 data. The model extends Kim Yoon’s Convolutional Neural Networks for Sentence Classification and Denny Britz’s work. The model was published along the Dual-CNN model in the paper: On Semantics and Deep Learning for Event Detection in Crisis Situations.
If you use this code/model please cite the following publication:
- On Semantics and Deep Learning for Event Detection in Crisis Situations Burel, Grégoire; Saif, Hassan; Fernandez, Miriam and Alani, Harith (2017). On Semantics and Deep Learning for Event Detection in Crisis Situations. In: Workshop on Semantic Deep Learning (SemDeep), at ESWC 2017, 29 May 2017, Portoroz, Slovenia.
Code
The CREES API code and models can be downloaded from GitHub.
Report an Issue
If you find any bug or have any issues with the API, you can add an issue to the (bug tracker)[https://github.com/evhart/crees/issues].
References
- Semantic Wide and Deep Learning for Detecting Crisis-Information Categories on Social Media Burel, Grégoire; Saif, Hassan and Alani, Harith (2017). Semantic Wide and Deep Learning for Detecting Crisis-Information Categories on Social Media. In: The Semantic Web – ISWC 2017. 2017, Vienna, Austria.
- On Semantics and Deep Learning for Event Detection in Crisis Situations Burel, Grégoire; Saif, Hassan; Fernandez, Miriam and Alani, Harith (2017). On Semantics and Deep Learning for Event Detection in Crisis Situations. In: Workshop on Semantic Deep Learning (SemDeep), at ESWC 2017, 29 May 2017, Portoroz, Slovenia.
- COMRADES H2020 European Project
- CrisLex Datasets
- Convolutional Neural Networks for Sentence Classification
- Implementing a CNN for Text Classification in TensorFlow
Acknowledgment
This work has received support from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 687847 (COMRADES).