Hands-On Question Answering Systems with Bert: Applications in Neural Networks and Natural Language Processing

Chapter 1: Introduction to Natural Language ProcessingChapter Goal: To introduce basics of natural language processing1.1 What is natural language processing1.2 What is natural language understanding1.3 Natural language processing tasks1.3.1 Tokenization1.3.2 Stemming and lemmatization1.3.3 Bag of words1.3.4 Word / Sentence vectorization
Chapter 2: Introduction to Word Embeddings
Chapter Goal: To introduce the basics of word embeddings3.1 What is word embeddings3.2 Different methods of word embeddings3.2.1 Word2vec3.2.2 Glove3.2.3 Elmo3.2.4 Universal sentence encoders3.2.5 BERT3.3 Bidirectional Encoder Representations from Transformers (BERT)3.3.1 BERT - base3.3.2 BERT - large
Chapter 3: BERT Algorithms ExplainedChapter Goal: Details on BERT model algorithms4.1 Masked language model4.2 Next sentence prediction (NSP) 4.3 Text classification using BERT4.4 Various types of BERT based models4.4.1 ALBERT4.4.2 ROBERT4.4.3 DistilBERT
Chapter 4: BERT Model Applications - Question Answering SystemChapter Goal: Details on question answering system5.1 Introduction5.2 Types of QA systems5.3 QA system design using BERT5.4 DrQA system5.5 DeepPavlov QA system
Chapter 5: BERT Model Applications - Other tasksChapter Goal: Details on NLP tasks performed by BERT.6.1 Introduction6.2 Other NLP Tasks: 6.2.1 Sentiment analysis 6.2.2. Named entity recognition 6.2.3 Tag generation 6.2.4 Classification 6.2.5 Text summarization 6.2.6 Language translation
Chapter 6: Future of BERT modelsChapter Goal: Provides an introduction to the new advances in the areas NLP using BERT7.1 BERT - Future capabilities