(Downloads - 0)
For more info about our services contact : help@bestpfe.com
Table of contents
1 Introduction
1.1 Sentiment Analysis
1.1.1 Non-Neural Sentiment Analysis
1.1.2 Neural Sentiment Analysis
1.2 Automatic summarization
1.2.1 Non-Neural Text Summarization
1.2.2 Neural Text Summarization
1.3 Thesis Outline
1.3.1 Thesis contributions
Part I. Sentiment Recognition
2 RelatedWork
2.1 Neural Networks architectures for sentiment analysis
2.2 Sentiment analysis in dialogues
3 Impact of Neural Networks depth for sentiment analysis
3.1 Introduction
3.2 Preliminary analysis of sentiment transfer by a Deep CNN
3.2.1 Motivation
3.2.2 Twitter data
3.2.3 Transfer learning results
3.2.4 Conclusion
3.3 DenseNet
3.3.1 Skip-connections
3.3.2 Dense Connectivity
3.3.3 Convolutional Block and Transitional Layer
3.4 Evaluation
3.5 Discussion
3.6 Conclusion
4 Dialogue acts and sentiment analysis
4.1 Introduction
4.2 Mastodon Corpus
4.3 Multi-task model
4.3.1 Model description
4.3.2 Training procedure
4.4 Evaluation
4.4.1 Multi-task experiments
4.4.2 Transfer between tasks
4.5 Analysis
4.6 Conclusion
Part II. Sentence Compression
5 Related work
5.1 Neural Sentence Summarization
5.2 Neural Text-to-text Generation
6 RL sentence compression
6.1 Introduction
6.2 Extraction of Dependency Subtrees
6.3 Model
6.3.1 Extractor Network
6.3.2 Abstractor Network
6.3.3 Reinforce Extraction
6.4 Evaluation
6.4.1 Full Select-and-Paraphrase Model
6.4.2 Oracle Setting
6.5 Conclusion
7 Enriching summarization with syntactic knowledge
7.1 Introduction
7.2 Models
7.2.1 Baseline
7.2.2 Integrating Syntax
7.2.3 Reinforcement Learning
7.3 Evaluation
7.4 Analysis
7.5 Conclusion
8 Conclusion
8.1 Summary and Conclusions
8.2 Directions for Future Research
Bibliography
