Convolutional Neural Networks (CNNs)

For more info about our services contact : help@bestpfe.com

Table of contents

Résumé
Acknowledgements
1 Introduction
1.1 Contributions of this thesis
1.2 Structure and outline of the thesis
2 State-of-the-art
2.1 Event Extraction
2.1.1 Event Extraction approaches
2.1.2 Pattern-based approaches
2.1.3 Feature-based approaches
2.1.4 Neural-based approaches
2.2 Event extraction evaluation
2.3 In-depth analysis of the state-of-the-art approaches
2.4 Conclusions
3 Event Detection
3.1 Background theory
3.1.1 Multi-Layer Perceptrons (MLPs)
3.1.2 Training neural networks
3.1.3 Optimization problem
3.1.4 Regularization
3.1.5 Gradient-based learning
3.1.6 Convolutional Neural Networks (CNNs)
3.2 Word embeddings
3.2.1 Neural language model
3.2.2 Collobert&Weston (C&W)
3.2.3 Word2vec
3.2.4 FastText
3.2.5 Dependency-based
3.2.6 GloVe
3.2.7 Conclusions
3.3 Event Detection
3.3.1 What is an event trigger?
3.3.2 Corpus analysis
3.3.3 Event Detection CNN
3.3.4 Evaluation framework
3.3.5 Results and comparison with existing systems
3.3.6 Word embeddings analysis
3.3.7 Retrofitting
3.4 Conclusions
4 Deep neural network architectures for Event Detection
4.1 Background theory
4.1.1 Recurrent Neural Networks (RNNs)
4.1.2 Long Short-Term Memory Units (LSTMs)
4.1.3 Bidirectional RNNs
4.1.4 Training RNNs
4.2 Exploiting sentential context in Event Detection
4.2.1 Sentence embeddings
4.2.2 Sentence encoder
4.2.3 Event Detection with sentence embeddings
4.2.4 Results
4.3 Exploiting the internal structure of words for Event Detection
4.3.1 Character-level CNN
4.3.2 Model
4.3.3 Data augmentation
4.3.4 Results
4.4 Conclusions
5 Argument role prediction
5.1 What are event arguments?
5.2 Links with Relation Extraction
5.3 CNN model for argument role prediction
5.4 The influence of Event Detection on arguments
5.5 Results
5.6 Conclusions
6 Conclusions
6.1 Summary of the contributions of the thesis
6.2 Future work
Bibliography