Intelligent Natural Language Processing: Trends and Applications / / edited by Khaled Shaalan, Aboul Ella Hassanien, Fahmy Tolba

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2018
• Edizione: 1st ed. 2018.
• Descrizione fisica: 1 online resource (X, 776 p. 215 illus., 142 illus. in color.)
• Disciplina: 006.35
• Soggetto topico: Computational intelligence; Natural language processing (Computer science); Computational linguistics; Big data; Computational Intelligence; Natural Language Processing (NLP); Computational Linguistics; Big Data
• Persona (resp. second.): ShaalanKhaled; HassanienAboul Ella; TolbaFahmy
• Nota di contenuto: Intro -- Preface -- Contents -- Sentiment Analysis -- 1 Using Deep Neural Networks for Extracting Sentiment Targets in Arabic Tweets -- Abstract -- 1 Introduction -- 2 Background -- 3 Data Collection and Annotation -- 4 Building Word Embeddings -- 5 The Implemented Models -- 5.1 The Baseline Model -- 5.2 The Deep Neural Network Model -- 5.2.1 Bidirectional Long Short-Term Memory Networks (BI-LSTMs) -- 5.2.2 The Conditional Random Fields (CRF) Tagging Model -- 5.2.3 BI-LSTM-CRF -- 6 Performance Evaluation -- 7 Conclusion -- Acknowledgements -- References -- 2 Evaluation and Enrichment of Arabic Sentiment Analysis -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Challenges Arabic Sentiment Analysis -- 3.1 Encoding -- 3.2 Sentiment Analysis Impacted Due to Unavailability of Punctuations -- 3.3 Excess Resources Required -- 3.4 Sarcastic Tamper -- 3.5 One Word Represents Two Polarities -- 3.6 Indifferent Writing Style -- 3.7 Free Writing Style -- 3.8 Word Short Forms -- 3.9 Same Word Usage for Both Polarities -- 4 Data Collection -- 5 Implementation of Arabic Sentiment Analysis -- 6 Evaluation and Results -- 7 Conclusion -- References -- 3 Hotel Arabic-Reviews Dataset Construction for Sentiment Analysis Applications -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Arabic Sentiment Analysis -- 4 Hotel Arabic Reviews Dataset (HARD) -- 4.1 Collection -- 4.2 Properties -- 5 Sentiment Analysis -- 5.1 Text Pre-processing -- 5.2 Feature Extraction -- 5.3 Classifiers -- 6 Experimental Results -- 6.1 Bag of Words -- 6.2 Lexicon-Based Classification -- 7 Conclusions -- References -- 4 Using Twitter to Monitor Political Sentiment for Arabic Slang -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Corpus Collection and Preparation -- 3.2 Pre-processing -- 3.3 Text Classification -- 4 Results and Evaluation. ; 5 Conclusion and Future Work -- References -- Estimating Time to Event of Future Events Based on Linguistic Cues on Twitter -- 1 Introduction -- 2 Related Research -- 3 Time-to-Event Estimation Method -- 4 Experimental Set-Up -- 4.1 Data Sets -- 4.2 Features -- 4.3 Training and Test Regimes -- 4.4 Evaluation and Baselines -- 4.5 Hyperparameter Optimization -- 5 Test Results -- 6 Discussion -- 7 Conclusions and Future Work -- References -- Machine Translation -- Automatic Machine Translation for Arabic Tweets -- 1 Introduction -- 2 Arabic Language Challenges Within NLP and Social Media -- 2.1 Modern Standard Arabic Challenges for MT -- 2.2 Arabic Language in Microblogs -- 3 Overview of Statistical Machine Translation -- 3.1 Language Model -- 3.2 Word Alignment -- 3.3 Translation Model -- 3.4 Decoding -- 4 Translating Arabic Tweets -- 4.1 Data Collection -- 4.2 Data Collection -- 4.3 Experiments -- 4.4 Results -- 4.5 Discussion -- 5 Conclusion and Future Work -- References -- Developing a Transfer-Based System for Arabic Dialects Translation -- 1 Introduction -- 2 Related Studies -- 3 Arabic Language Variation -- 4 Machine Translation Paradigms -- 4.1 Rule Based MT -- 4.2 Statistical MT -- 4.3 Hybrid MT -- 5 (ALMoFseH) Arabic Dialects Machine Translation -- 6 Methodology -- 6.1 Building a Lexical Database -- 6.2 The Transfer System -- 6.3 Naive Bayesian Classifier (NB) -- 6.4 Rewrite Rules for Dialectal Normalization -- 6.5 Functional Model -- 7 Evaluation of the System -- 8 Results -- 9 Conclusion -- References -- 8 The Key Challenges for Arabic Machine Translation -- Abstract -- 1 Introduction -- 2 Challenges for Arabic Translation -- 2.1 Classical Arabic -- 2.2 Modern Standard Arabic -- 2.3 Dialect Arabic -- 3 Machine Translation in Natural Language Processing -- 3.1 Metaphor Translation -- 3.2 Metaphor in Holy Quran. ; 3.3 Metaphor in Modern Standard Arabic -- 3.4 Metaphor in Dialect Arabic -- 4 Named Entity Recognition Translation -- 5 Word Sense Disambiguation Translation -- 6 Conclusion -- References -- Information Extraction -- Graph-Based Keyword Extraction -- 1 Introduction -- 2 Related Work -- 3 Research Methodology -- 3.1 Overview -- 3.2 The Proposed Methodology -- 3.3 Dataset -- 3.4 Data Processing -- 3.5 Learn Classifier and TF/IDF -- 3.6 Performance Evaluation -- 4 Discussion -- 5 Conclusion and Future Prospects -- References -- 10 CasANER: Arabic Named Entity Recognition Tool -- Abstract -- 1 Introduction -- 2 State of the Art on NER Systems -- 2.1 Previous NE Categorization -- 2.2 NER Approaches and Systems -- 3 ANE Identification and Categorization -- 3.1 Identification of the ANE Forms and Categories -- 3.2 Relationship Between ANEs -- 4 Proposed Method -- 4.1 Analysis Transducer Establishment -- 4.2 Synthesis Transducer Establishment -- 5 Implementation and Evaluation -- 6 Conclusion -- References -- 11 Semantic Relations Extraction and Ontology Learning from Arabic Texts-A Survey -- Abstract -- 1 Introduction -- 2 Arabic Semantic Relation Extraction and Ontology Learning -- 3 Arabic Semantic Relation Extraction -- 3.1 Semantic Relation Extraction Between Arabic Named Entities -- 3.1.1 Rule-Based Approach -- 3.1.2 Machine Learning Approach -- 3.1.3 Hybrid Approach -- 3.2 Semantic Relation Extraction Between Arabic Ontological Concepts -- 4 Arabic Ontology Learning -- 4.1 Upper Ontology -- 4.1.1 Arabic WordNet Ontology -- 4.1.2 Formal Arabic Ontology -- 4.2 Domain Ontology -- 4.2.1 General Domains -- Manual Approach -- Statistical Approach -- Linguistic Approach -- Hybrid Approach -- Uncategorized -- 4.2.2 Islamic Domain -- Quran Ontology -- Hadith Ontology -- 5 Conclusion -- Information Retrieval and Question Answering. ; 12 A New Semantic Distance Measure for the VSM-Based Information Retrieval Systems -- Abstract -- 1 Introduction -- 2 The Proposed Approach -- 2.1 A Novel Indexing Approach -- 2.2 The Significance Level of a Concept (SLC) -- 2.3 Semantic Distance Between Query and CS -- 3 System Architecture -- 4 Experimental Analysis -- 4.1 Experimental Setup -- 4.2 Experiments, Results, and Evaluation -- 4.2.1 The Conceptualization Levels -- 4.2.2 The Retrieval Capability -- 4.2.3 The Ranking Accuracy -- 5 Conclusion and Future Work -- Appendix: The Implementation Algorithms -- References -- An Empirical Study of Documents Information Retrieval Using DWT -- 1 Introduction -- 2 Background -- 2.1 Term Signal -- 2.2 Weighting Scheme -- 2.3 Document Segmentation -- 2.4 Wavelet Transform Algorithm -- 3 Design Issues and Implementation of Information Retrieval Using DWT -- 3.1 Problems and Design Issues -- 3.2 Implementation of the Suggested Model -- 3.3 Document Segmentation -- 3.4 Term Weighting -- 4 Experiments and Results -- 5 Conclusion -- References -- 14 A Review of the State of the Art in Hindi Question Answering Systems -- Abstract -- 1 Introduction -- 2 A Typical Pipeline Architecture of a Question Answering System -- 2.1 Question Processing -- 2.1.1 Question Classification -- 2.2 Answer Type Determination -- 2.3 Keyword Extraction -- 2.4 Query Expansion -- 2.5 Document Processing -- 2.5.1 Passage Retrieval -- 2.6 Answer Extraction -- 2.6.1 Named Entity Recognition -- 2.6.2 Answer Scoring and Ranking -- 2.6.3 Answer Presentation -- 3 Developments in Hindi Question Answering System -- 3.1 Developments in Tasks of Question Answering Systems -- 4 Introduction to Hindi Language and Its Challenges for QASs -- 5 Tools and Resources for Hindi Question Answering -- 6 Future Scopes -- References -- Text Classification. ; 15 Machine Learning Implementations in Arabic Text Classification -- Abstract -- 1 Introduction -- 2 Problem Definition -- 2.1 Problem Scope, Input and Output -- 2.2 Problem Formalization -- 3 Text Classification Steps -- 3.1 Data Selection and Preparation -- 3.2 Text Preprocessing -- 3.3 Document Indexing and Term Weighting Methods -- 3.4 Feature Reduction -- 4 Classification Algorithms -- 5 Arabic Text Classification -- 6 Directions for Further Research -- 7 Conclusion -- References -- Authorship and Time Attribution of Arabic Texts Using JGAAP -- 1 Introduction -- 2 Background -- 2.1 Authorship Attribution and NLP -- 2.2 Authorship Attribution in Arabic -- 3 Data -- 3.1 Corpus Description -- 3.2 Selection of Texts -- 4 Methods -- 4.1 JGAAP -- 4.2 Canonicizers -- 4.3 Event Drivers -- 4.4 Analysis Methods -- 5 Results -- 5.1 Character n-grams -- 5.2 Word n-grams -- 5.3 Word Length -- 5.4 Rare Words -- 5.5 Most Common Words -- 6 Analysis of Errors -- 7 Future Work and Conclusions -- References -- 17 Automatic Text Classification Using Neural Network and Statistical Approaches -- Abstract -- 1 Reviewing the Previous Work -- 2 Preprocessing Procedures for the Two Proposed Classifiers -- 2.1 Word Extraction -- 2.2 Stop Words Removal -- 2.3 Word Stemming -- 2.4 Improvements -- 2.5 Reuters 21,758 Test Collection for Text Categorization -- 2.6 Term Weighting Techniques -- 3 The Proposed Statistical Classifier -- 3.1 Converting the Text Documents into a Database -- 3.2 The Resulting Database Model -- 3.3 Weighting Techniques -- 3.4 Improvements for Weighting -- 3.5 Experimental Details -- 4 Neural Network Based Classifier -- 4.1 Dimensionality Reduction for Text Categorization -- 4.2 The Proposed Neural Network Based Text Classifier -- 4.3 Experimental Details -- 5 Comparison Between Proposed Statistical Classifier and the Neural Network Based Classifier. ; 6 Conclusions.
• Sommario/riassunto: This book brings together scientists, researchers, practitioners, and students from academia and industry to present recent and ongoing research activities concerning the latest advances, techniques, and applications of natural language processing systems, and to promote the exchange of new ideas and lessons learned. Taken together, the chapters of this book provide a collection of high-quality research works that address broad challenges in both theoretical and applied aspects of intelligent natural language processing. The book presents the state-of-the-art in research on natural language processing, computational linguistics, applied Arabic linguistics and related areas. New trends in natural language processing systems are rapidly emerging – and finding application in various domains including education, travel and tourism, and healthcare, among others. Many issues encountered during the development of these applications can be resolved by incorporating language technology solutions. The topics covered by the book include: Character and Speech Recognition; Morphological, Syntactic, and Semantic Processing; Information Extraction; Information Retrieval and Question Answering; Text Classification and Text Mining; Text Summarization; Sentiment Analysis; Machine Translation Building and Evaluating Linguistic Resources; and Intelligent Language Tutoring Systems.
• Titolo autorizzato: Intelligent Natural Language Processing: Trends and Applications
• ISBN: 3-319-67056-5
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910299888803321
• Lo trovi qui: Univ. Federico II
• Serie: Studies in Computational Intelligence, . 1860-949X ; ; 740