de
en
Schliessen
Detailsuche
Bibliotheken
Projekt
Impressum
Datenschutz
zum Inhalt
Detailsuche
Schnellsuche:
OK
Ergebnisliste
Titel
Titel
Inhalt
Inhalt
Seite
Seite
Im Dokument suchen
Jebbara, Soufian: Neural Approaches to Relational Aspect-Based Sentiment Analysis. Exploring generalizations across words and languages. 2020
Inhalt
Abstract
Acknowledgments
Introduction
Motivation
Aspect-Based Sentiment Analysis
Terminology
Challenges
Research Questions
Contributions and Structure of the Thesis
Publications
Background
Artificial Neural Networks
Feed-Forward Neural Networks
Convolutional Neural Networks
Recurrent Neural Networks
Representing Textual Data
Word embeddings
Sequence Labeling
Tagging Schemes
Metrics
Relational Sentiment Analysis
Introduction
Contributions and Structure of the Chapter
A Relational Framework for Aspect-Based Sentiment Analysis
Opinion Target and Opinion Phrase Extraction
Domain-Specific Word Embeddings
Part-of-Speech Tags
Convolutional Neural Network Model
Recurrent Neural Network Model
Stacked Model
Joint Opinion Target and Opinion Phrase Extraction
Opinion-Phrase-Specific Sentiment Classification
Position-Aware Recurrent Neural Network
Relation Extraction
Experimental Evaluation and Discussion
Datasets
Experimental Settings
Evaluation: Domain-Specific Word Embeddings
Evaluation: Opinion Target and Opinion Phrase Extraction
Evaluation: Opinion-Phrase-Specific Sentiment Classification
Evaluation: Opinion-Target Relation Extraction
Discussion and Future Work
Conclusion
Aspect-Based Sentiment Analysis and Structured Resources
Introduction
Contributions and Structure of the Chapter
A Two-Step Approach for Aspect-Based Sentiment Analysis
Domain-Specific Word Embeddings
Part-of-Speech Tags
Opinion Target Extraction
Target-Specific Sentiment Classification
Retrofitting Word Embeddings to WordNet
Extracting Word-Level Features from SenticNet
Experimental Evaluation and Discussion
Dataset
Opinion Target Extraction
Target-Specific Sentiment Classification
Conclusion
Subword Information for Opinion Target Extraction
Introduction
Contributions and Structure of the Chapter
Baseline Model
Character-Enhanced Model
Experimental Evaluation and Discussion
Dataset
Experimental Settings
Overall Performance
Suffix Information
Out-of-Vocabulary Errors
Multi-Word Expressions
Conclusion
Zero-Shot Cross-Lingual Opinion Target Extraction
Introduction
Contributions and Structure of Chapter
Monolingual Model
Cross-Lingual Model
Aligning Word Embeddings across Languages
Cross-lingual Transfer
Experimental Evaluation and Discussion
Datasets
Experimental Settings
Zero-Shot Transfer Learning
Cross-Lingual Transfer Learning with Additional Target Language Data
Comparison of Alignment Methods
Comparison to State-of-the-Art
Discussion
Conclusion
Conclusion
Summary
Outlook
List of Tables
List of Figures
Acronyms
Bibliography