A Handbook of Computational Linguistics: Artificial Intelligence in Natural Language Processing

Name: A Handbook of Computational Linguistics: Artificial Intelligence in Natural Language Processing | Handbook of Computational Linguistics: Artificial Intelligence in Natural Language Processing
Brand: De Gruyter
Price: 71.99 EUR
Availability: OnlineOnly

Handbook of Computational Linguistics: Artificial Intelligence in Natural Language Processing

Youddha Beer Singh Aditya Dev Mishra Pushpa Singh Dileep Kumar Yadav(Author)

De Gruyter (Publisher)

1st Edition

Published on 26. August 2024

400 pages

E-Book

PDF with digital watermarking

System requirements

978-981-5238-48-8 (ISBN)

€71.99incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Content

Intro
CONTENTS
Cover
Title
Copyright
End User License Agreement
Preface
KEY FEATURES
List of Contributors
A Comprehensive Study of Natural Language Processing
Rohit Vashisht1,*, Sonia Deshmukh1, Ambrish Gangal1 and Garima Singh1
1. INTRODUCTION
2. EMERGENCY OF NLP
3. WORKING MODEL OF NLP
4. MAJOR APPLICATION OF NLP
5. NLP'S PRIME CHALLENGES
CONCLUSION AND FUTURE DIRECTIONS
REFERENCES
Recent Advancements in Text Summarization with Natural Language Processing
Asha Rani Mishra1,* and Payal Garg1
1. INTRODUCTION
1.1. Evolution in NLP
1.2. Recent Advancement in NLP
1.3. Applications in NLP
1.4. Role of Natural Language Processing in Text Mining
1.5. Challenges in Handling Text Data
2. REVIEW OF NATURAL LANGUAGE PROCESSING CONCEPTS, TECHNIQUES, TRENDS, AND APPLICATIONS
3. NATURAL LANGUAGE PROCESSING (NLP) IN TEXT SUMMARIZATION
3.1. Nature of Text Summarization According to Input
3.2. Nature of Text Summarization According to Output
3.3. Challenges in Text Summarization Approaches
4. GENERATING SUMMARY USING EXTRACTIVE APPROACH
5. PROPOSED METHODOLOGY
5.1. Steps in Textrank Algorithm
6. RESULTS AND DISCUSSION
6.1. Spacy
6.2. NLTK
6.3. Sumy
6.4. ROUGE Scores as Evaluation Metrics for Generated Summary
CONCLUSION AND FUTURE SCOPE
REFERENCES
Learning Techniques for Natural Language Processing: An Overview
Shahina Anjum1,* and Sunil Kumar Yadav2
1. INTRODUCTION
1.1. Categorization of NLP
1.2. Natural Language Processing Phases
2. REVIEW OF NATURAL LANGUAGE PROCESSING
3. NATURAL LANGUAGE TECHNIQUES
3.1. Popular NLP Techniques
3.1.1. Support Vector Machines
3.1.2. Neural Networks
3.1.3. Deep Learning Models
3.2. Traditional NLP Techniques
3.2.1. Probabilistic Models
3.2.2. N-Gram Models
3.2.3. Hidden Markov Models
3.3. Advanced NLP Techniques
3.3.1. Transfer learning
a. Advantages of Performing Transfer Learning
3.3.2. Domain Adaptation
4. CATEGORIZATION OF NLP TECHNIQUES
5. ROLE OF NATURAL LANGUAGE PROCESSING IN LARGE PROJECTS
5.1. Challenges in NLP Learning Techniques
CONCLUSION
REFERENCES
Natural Language Processing: Basics, Challenges, and Clustering Applications
Subhajit Ghosh1,*
1. INTRODUCTION
2. REVIEW OF NLP CHALLENGES
3. NLP APPROACHES
4. TEXT CLUSTERING: AN ESSENTIAL TASK IN NLP
4.1. Challenges of Text Clustering
5. COMPUTATIONAL METHODOLOGY FOR TEXT CLUSTERING
5.1. Vector Space Model
5.2. Experiments with K-Means
5.3. Using GA
6. MACHINE TRANSLATION AND OTHER NLP APPLICATIONS
CONCLUSION
REFERENCES
Hybrid Approach to Text Translation in NLP Using Deep Learning and Ensemble Method
Richa Singh1, Rekha Kashyap1 and Nidhi Srivastava2
1. INTRODUCTION
2. REVIEW OF FEDERATED LEARNING
3. RECENT RESEARCH IN NLP USING DEEP LEARNING
4. PROBLEM IDENTIFICATION
5. PROPOSED SOLUTION
6. RESULT
7. DISCUSSION
CONCLUSION
REFERENCES
Deep Learning in Natural Language Processing
Rashmi Kumari1, Subhranil Das2, Raghwendra Kishore Singh3 and Abhishek Thakur4
1. INTRODUCTION
2. NLP COMPONENTS
2.1. NLU
2.2. NLG
3. DEEP LEARNING FOR TEXT REPRESENTATION
3.1. Word Embeddings
3.2. Sentence and Document Embeddings
4. DEEP LEARNING FOR TEXT CLASSIFICATION (TC)
5. DEEP LEARNING FOR SEQUENCE LABELLING
5.1. POS
5.2. NER
5.3. Chunking and Parsing
6. DEEP LEARNING FOR TEXT GENERATION
6. APPLICATIONS OF DEEP LEARNING IN NLP
CONCLUSION
REFERENCES
Deep Learning-Based Text Identification from Hazy Images: A Self-Collected Dataset Approach
Sandeep Kumar Vishwakarma1, Anuradha Pillai2 and Deepika Punj2
1. INTRODUCTION
2. LITERATURE SURVEY
2.1. Image Dehazing Methods
2.2. Text Detection Methods
3. METHODOLOGY AND FRAMEWORK
3.1. Algorithm
4. EXPERIMENTAL SETUP AND RESULTS
4.1. Evaluation Results
4.2. Comparison with Existing Methods
CONCLUSION
REFERENCES
Deep Learning-based Word Sense Disambiguation for Hindi Language Using Hindi WordNet Dataset
Preeti Yadav1, Sandeep Vishwakarma2 and Sunil Kumar3
1. INTRODUCTION
2. HINDI WORDNET
2.1. The Application Programming Interface for the Hindi Wordnet
3. LITERATURE REVIEW
4. PROPOSED APPROACH AND FRAMEWORK
5. EXPERIMENTAL SETUP AND RESULTS
CONCLUSION
REFERENCES
The Machine Translation Systems Demystifying the Approaches
Shree Harsh Attri1,* and Tarun Kumar2
1. INTRODUCTION
2. APPROACHES TO BILINGUAL MACHINE TRANSLATION
2.1. Rule-based Techniques
2.2. Interlingua Approach
2.3. Example-based Techniques
2.4. Statistical Techniques
2.5. Rule-Based MT vs. Statistical MT
2.6. Soft Computing based Techniques
2.7. Neural Networks-based Techniques
2.8. Fuzzy Theory-based Techniques
2.9. Genetic Algorithms-based Techniques
2.10. Hybrid Techniques
3. POS TAGGING IN MACHINE TRANSLATION
4. BILINGUAL PRE-PROCESSING TECHNIQUES
5. BILINGUAL MORPHOLOGICAL ANALYSES
6. BILINGUAL REVERSE MORPHOLOGICAL ANALYSIS
7. BILINGUAL POST-PROCESSING (PP) TECHNIQUES
CONCLUSION
REFERENCES
Machine Translation of English to Hindi with the LSTM Seq2Seq Model Utilizing Attention Mechanism
Sunil Kumar1,2,*, Sandeep Kumar Vishwakarma1, Abhishek Singh3, Rohit Tanwar4 and Digvijay Pandey5
1. INTRODUCTION
2. LITERATURE REVIEW
3. METHODOLOGY
3.1. Dataset
3.2. Data Preprocessing
3.3. Seq2Seq Model
3.4. LSTM
3.4.1. Uni-LSTM
3.4.2. Bi-LSTM
4. PROPOSED METHOD
4.1. LSTM Seq2Seq Model
4.2. Attention Mechanism
5. MATERIAL AND EXPERIMENTAL SETUP
5.1. Dataset and Source
5.2. Data Splitting
5.3. Data Preprocessing
5.4. Training
5.5. Evaluation
6. RESULT AND DISCUSSION
CONCLUSION
REFERENCES
Natural Language Processing: A Historical Overview, Current Developments, and Future Prospects
Neha Saini1, Neha 2 and Manjeet Singh3,*
1. INTRODUCTION
2. LEVELS OF NLP
3. NATURAL LANGUAGE GENERATION
4. HISTORY OF NLP
5. RELATED WORK
6. APPLICATIONS OF NLP
7. RECENT TRENDS IN NLP
8. FUTURE OF NLP
8.1. Advanced Language Understanding
8.2. Multilingual and Cross-lingual NLP
8.3. Better Contextual Understanding
8.4. Few-shot and Zero-shot Learning
8.5. Ethical and Responsible AI
8.6. Domain-Specific NLP
8.7. Conversational Agents and Virtual Assistants
8.8. NLP in Unstructured Data Analysis
8.9. Integration with Other Technologies
8.10. Continued Research and Innovation
CONCLUSION
REFERENCES
Recent Advances in Transfer Learning for Natural Language Processing (NLP)
Nitin Sharma1 and Bhumica Verma2,*
1. INTRODUCTION
2. KEY CONCEPTS AND ARCHITECTURES OF TRANSFER LEARNING
2.1. Fine-tuning: Adapting Pretrained Models to Specific Tasks
2.2. Multi-task Learning: Enhancing Model Performance with Shared Knowledge
2.3. Domain Adaptation: Bridging the Gap between Source and Target Domains
2.4. Knowledge Distillation: Transferring Knowledge from Complex Models to Compact Models
2.5. Zero-shot Learning: Learning to Simplify Unseen Classes
3. PRE-TRAINED LANGUAGE MODELS
3.1. GPT-3: A Breakthrough in Language Generation and Understanding
3.2. BERT: Transforming Natural Language Understanding
3.3. RoBERTa: Robustly Optimized BERT Approach
4. APPLICATIONS OF TRANSFER LEARNING IN NLP
4.1. Text Classification
4.2. Named Entity Recognition
4.3. Question Answering
4.4. Text Summarization
5. LIMITATIONS AND CHALLENGES OF TRANSFER LEARNING
5.1. Dataset Biases
5.2. Domain Adaptation
5.3. Generalization Ability
5.4. Model Interpretability
5.5. Recent Challenges in NLP
6. FUTURE DIRECTIONS AND RESEARCH OPPORTUNITIES
6.1. Investigating Transfer Learning in Low-Resource Languages
6.2. Developing Transfer Learning Techniques for Speech and Multimodal NLP Tasks
6.3. Other Potential Research Directions
CONCLUSION
REFERENCES
Beyond Syntax and Semantics: The Quantum Leap in Natural Language Processing
Ashish Arya1,* and Arti Ranjan2
1. INTRODUCTION
2. BACKGROUND: APPLICATIONS OF QUANTUM COMPUTING AND QNLP
3. NATURAL LANGUAGE PROCESSING
3.1. Tokenization
3.2. Part-of-Speech (POS) Tagging
3.3. Named Entity Recognition (NER)
3.4. Sentiment Analysis
3.5. Parsing
3.6. Machine Translation
3.7. Information Retrieval
4. QUANTUM COMPUTING PRIMER
4.1. Emergence of Quantum Computing
4.2. Quantum Mechanics and Quantum Computing
4.2.1. Wave-particle Duality
4.2.2. Superposition
4.2.3. Coherence
4.2.4. Entanglement
4.2.5. Measurement
4.3. Continuous Variable Quantum Computing (CVQC)
4.4. Gate-based Quantum Computing
4.4.1. Qubits
4.4.2. Bloch Sphere Representation
4.4.3. Measurement
4.4.4. Single Qubit Gates
4.4.5. Two Qubit Gates
4.4.6. Multi-Qubit Gates
4.5. Quantum Circuit
5. QUANTUM NATURAL LANGUAGE PROCESSING (QNLP)
6. QNLP ALGORITHMS
6.1. Quantum Embedding
6.1.1. Basis Embedding
6.1.2. Amplitude Embedding
6.2. Quantum Machine Learning (QML)
6.2.1. Quantum Approximate Optimization Algorithm (QAOA)
6.2.2. Quantum PCA
6.3. Quantum Algorithms for NLP
6.3.1. DisCoCat
6.4. Quantum Language Models
6.5. Quantum Natural Language Understanding (QNLU)
6.6. Quantum Text Compression
7. CHALLENGES AND LIMITATIONS OF QLNP
8. HYBRID QUANTUM CLASSICAL MODELS
8.1. Variational Quantum Eigensolver
8.1.1. VQE for NLP
8.1.2. Discussion
CONCLUSION
FUTURE DIRECTIONS
REFERENCES
Text Extraction from Blurred Images through NLP-based Post-processing
Arti Ranjan1,* and M. Ravinder1
1. INTRODUCTION
1.1. Overview of Text Extraction From Blurred Images
1.2. Traditional Image Processing Techniques for Text Extraction
2. NLP-BASED POST-PROCESSING TECHNIQUES FOR TEXT EXTRACTION FROM BLURRED IMAGES
2.1. Introduction to Natural Language Processing Techniques
2.2. NLP Pipeline
2.3. Named Entity Recognition for Text Extraction
2.4. Part-of-speech Tagging for Text Extraction
2.5. Machine Learning Algorithms for Enhancing NLP-based Post-Processing Techniques
2.6. Convolutional Neural Networks (CNNs) for Enhancing the Performance of NLP-based Post-processing
3. CASE STUDY: IMPROVING TEXT EXTRACTION FROM BLURRED IMAGES USING NLP-BASED POST-PROCESSING
3.1. Text Extraction from Blurred Images using Nlp Framework
3.2. Effectiveness of NLP-based Post-processing Techniques
4. COMPARISON WITH TRADITIONAL TEXT EXTRACTION TECHNIQUES
5. FUTURE DIRECTION AND CHALLENGES
CONCLUSION
REFERENCES
Speech-to-Sign Language Translator Using NLP
Vibhor Harit1, Nitin Sharma1, Aastha Tiwari1, Aditya Kumar Yadav1 and Aayushi Chauhan1
1. INTRODUCTION
2. METHODOLOGY USED
2.1. Methods and Techniques
2.2. Speech to Text Conversion
2.3. Text Analysis
2.3.1. Tokenization
2.3.2. Stop Word Removal
2.3.3. Stemming
2.3.4. Lemmatization
2.3.5. Syntax Tree Generation
2.3.6. POS Tagging
2.4. Sign Language Gesture Generation
2.5. Display the Sign Language Gestures
3. RESULT AND DISCUSSION
CASE I
CASE II
CASE III
CONCLUSION
REFERENCES
Speech Technologies
Archana Verma1,*
1. INTRODUCTION
1.1. Application Areas of Speech Technology
2. SPEECH RECOGNITION
2.1. Speech Analysis
2.2. Feature Extraction
3. MODELLING AND MATCHING
3.1. Speech Verification
4. REAL TIME SPEECH TO TEXT CONVERSION
4.1. Recognition of Speech
4.2. CAN
4.3. CART
5. INTERACTIVE VOICE RESPONSE SYSTEMS
6. SPEECH SYNTHESIS
6.1. Hidden Markov Model Based Speech Synthesis
7. SPEECH ANALYTICS
CONCLUSION
REFERENCES
The Linguistic Frontier: Unleashing the Power of Natural Language Processing in Cybersecurity
Aviral Srivastava1,* and Viral Parmar2
1. INTRODUCTION
1.1. Natural Language Processing: An Overview
1.2. The Relevance of NLP in Cybersecurity
2. APPLICATIONS OF NLP IN CYBERSECURITY
2.1. Malware Classification and Detection
2.2. Detection of Attacks Based on Social Engineering
2.3. Cyber Threat Intelligence Analysis
2.4. Roboticization of Emergency Procedures
2.5. Conversational AI for Security Operations
2.6. Secure Code Review
2.7. Privacy Policy Analysis
2.8. Cybersecurity Training and Awareness
2.9. Dark Web Analysis
2.10. Predictive Analytical Models for Online Dangers
3. CHALLENGES AND CONSIDERATIONS
3.1. Data Quality and Availability
3.2. Domain-Specific Language and Context
3.3. Privacy and Ethical Concerns
3.4. Scalability and Real-time Processing
4. LITERATURE REVIEW
5. FUTURE RESEARCH DIRECTIONS
5.1. Improved NLP Algorithms for Cybersecurity
5.2. Cross-Domain Integration and Collaboration
5.3. Adversarial NLP and Robustness
5.4. Explainable AI and Trustworthiness
CONCLUSION
REFERENCES
Recent Challenges and Advancements in Natural Language Processing
Gagan Gurung1,*, Rahul Shah1 and Dhiraj Prasad Jaiswal1
1. INTRODUCTION
2. COMPONENTS OF NLP
2.1. Natural Language Understanding
2.2. Natural Language Generation (NLG)
2.3. Working Process of NLP
3. NLP - THEN AND NOW
4. NLP TECHNIQUES
4.1. Tokenization
4.2. Part-of-speech (POS) Tagging
4.3. Named Entity Recognition (NER)
4.4. Sentiment Analysis
4.5. Text Classification
4.6. Machine Translation
4.7. Text Generation
4.8. Information Retrieval
4.9. Text Summarization
4.10. Dependency Parsing
5. NLP MODELS
5.1. Word2Vec is an NLP Model Widely Employed for Producing Word Embeddings
5.2. GloVe, Another well-known NLP Model
5.3. FastText, an Extension of Word2Vec that Incorporates Subword Information
5.4. Recurrent Neural Networks (RNNs) are an Essential Element in Natural Language Processing (NLP)
5.5. The Transformer Model Introduced An Innovative Architecture For Sequence-To-Sequence Tasks in NLP
5.6. Generative Pre-Trained Transformer
5.7. BERT, or Bidirectional Encoder Representations from Transformers
5.8. XLNet is Another Pre-trained Model that Utilizes Both Autoregressive Framework
6. RESULT AND DISCUSSION
CONCLUSION
REFERENCES
Subject Index
Back Cover

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

A Handbook of Computational Linguistics: Artificial Intelligence in Natural Language Processing

Description

More details

Content

System requirements