Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling

Jan 15, 2020
Gilles Vandewiele, Isabelle Dehaene, György Kovács, Lucas Sterckx, Olivier Janssens, Femke Ongenae, Femke De Backere, Filip De Turck, Kristien Roelens, Johan Decruyenaere, Sofie Van Hoecke, Thomas Demeester


  Access Model/Code and Paper
Block-wise Dynamic Sparseness

Jan 14, 2020
Amir Hadifar, Johannes Deleu, Chris Develder, Thomas Demeester


  Access Model/Code and Paper
System Identification with Time-Aware Neural Sequence Models

Nov 21, 2019
Thomas Demeester

* 34th AAAI Conference on Artificial Intelligence (AAAI 2020) 

  Access Model/Code and Paper
DeepProbLog: Neural Probabilistic Logic Programming

Jul 18, 2019
Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt

* Submitted to AIJ. Extended version of DeepProbLog: Neural Probabilistic Logic Programming (previously published at NeurIPS 2018). arXiv admin note: text overlap with arXiv:1805.10872 

  Access Model/Code and Paper
Sub-event detection from Twitter streams as a sequence labeling problem

Mar 13, 2019
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

* NAACL 2019 

  Access Model/Code and Paper
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

Aug 28, 2018
Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, Thomas Demeester

* Accepted at EMNLP 2018 

  Access Model/Code and Paper
Predefined Sparseness in Recurrent Sequence Models

Aug 27, 2018
Thomas Demeester, Johannes Deleu, Fréderic Godin, Chris Develder

* the SIGNLL Conference on Computational Natural Language Learning (CoNLL, 2018) 

  Access Model/Code and Paper
Adversarial training for multi-context joint entity and relation extraction

Aug 21, 2018
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

* EMNLP 2018 

  Access Model/Code and Paper
Joint entity recognition and relation extraction as a multi-head selection problem

Aug 16, 2018
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

* Expert Systems with Applications, Volume 114, 30 December 2018, Pages 34-45, ISSN 0957-4174 
* Preprint - Accepted for publication in Expert Systems with Applications 

  Access Model/Code and Paper
Prior Attention for Style-aware Sequence-to-Sequence Models

Jun 25, 2018
Lucas Sterckx, Johannes Deleu, Chris Develder, Thomas Demeester

* 6 pages, 6 figures 

  Access Model/Code and Paper
Jack the Reader - A Machine Reading Framework

Jun 20, 2018
Dirk Weissenborn, Pasquale Minervini, Tim Dettmers, Isabelle Augenstein, Johannes Welbl, Tim Rocktäschel, Matko Bošnjak, Jeff Mitchell, Thomas Demeester, Pontus Stenetorp, Sebastian Riedel

* Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2018), System Demonstrations 

  Access Model/Code and Paper
An attentive neural architecture for joint segmentation and parsing and its application to real estate ads

Mar 19, 2018
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

* Expert Systems with Applications, Volume 102, 15 July 2018, Pages 100-112, ISSN 0957-4174 
* Preprint - Accepted for publication in Expert Systems with Applications 

  Access Model/Code and Paper
Character-level Recurrent Neural Networks in Practice: Comparing Training and Sampling Schemes

Jan 09, 2018
Cedric De Boom, Thomas Demeester, Bart Dhoedt

* 23 pages, 11 figures, 4 tables 

  Access Model/Code and Paper
Break it Down for Me: A Study in Automated Lyric Annotation

Aug 11, 2017
Lucas Sterckx, Jason Naradowsky, Bill Byrne, Thomas Demeester, Chris Develder

* To appear in Proceedings of EMNLP 2017 

  Access Model/Code and Paper
Adversarial Sets for Regularising Neural Link Predictors

Jul 24, 2017
Pasquale Minervini, Thomas Demeester, Tim Rocktäschel, Sebastian Riedel

* Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI), 2017 

  Access Model/Code and Paper
Lifted Rule Injection for Relation Embeddings

Sep 23, 2016
Thomas Demeester, Tim Rocktäschel, Sebastian Riedel

* Camera-ready version for EMNLP 2016 Conference 

  Access Model/Code and Paper
Representation learning for very short texts using weighted word embedding aggregation

Jul 02, 2016
Cedric De Boom, Steven Van Canneyt, Thomas Demeester, Bart Dhoedt

* 8 pages, 3 figures, 2 tables, appears in Pattern Recognition Letters 

  Access Model/Code and Paper
Efficiency Evaluation of Character-level RNN Training Schedules

May 09, 2016
Cedric De Boom, Sam Leroux, Steven Bohez, Pieter Simoens, Thomas Demeester, Bart Dhoedt

* 3 pages, 3 figures 

  Access Model/Code and Paper
Knowledge Base Population using Semantic Label Propagation

Mar 03, 2016
Lucas Sterckx, Thomas Demeester, Johannes Deleu, Chris Develder

* Submitted to Knowledge Based Systems, special issue on Knowledge Bases for Natural Language Processing 

  Access Model/Code and Paper
Learning Semantic Similarity for Very Short Texts

Dec 02, 2015
Cedric De Boom, Steven Van Canneyt, Steven Bohez, Thomas Demeester, Bart Dhoedt

* 6 pages, 5 figures, 3 tables, ReLSD workshop at ICDM 15 

  Access Model/Code and Paper