Artificial Intelligence for Natural Language Processing (Hardcover, 1)

Chapter I. Introduction and word level analysis History, generic NLP system, levels and stages, ambiguity and challenges, words, corpora, morphology analysis, inflectional and derivational morphology, stemming, lemmatization, normalization, tokenization, bag of words, regular expression, finite automa, finite state transducers (FST), n grams language model. Chapter II. Syntactic analysis Part of Speech (POS) tagging: rule based and stochastic tagging, stop words, sequence labelling: HMM, Conditional Random Field (CRF), Context Free Grammars (CFG), Parsing: top down, Earley parsing, and CKY parsing, Probabilistic Context Free Grammars (PCFG), Term Frequency and Inverse Document Frequency (TF-IDF), information extraction, relation extraction. Chapter III. Semantic Analysis Semantic grammars, lexical semantics, relations among lexemes and their senses, homonymy, polysemy, synonymy, hyponymy, wordNet, word similarity, Word Sense Disambiguation (WSD), dictionary based approach of WSD, information retrieval. Chapter IV. Discourse and Pragmatic Analysis Discourse, cohesion, cohesive, discourse structure, adjacency pairs, ethnography of speaking, implicature, cooperative principle, schema- script, conversational analysis, interpretation, Endophora, Exophora, context and its types, Speech acts: Direct and indirect, Deixis and deictic expressions, Positive face and negative face in pragmatics, pragmatic markers and functions. Chapter V. Artificial Intelligence in NLP Artificial Intelligence in context of NLP, Supervised Machine learning (ML), Unsupervised ML, ML on natural language sentences, Hybrid ML systems for NLP, Introduction for deep learning for NLP, Applications: sentiment analysis, and prediction of next word, Case study: Language Understanding (LUIS), text summarization, text conversion, and chat-bots.