NLP-Lecture 1 PDF

# Natural Language Processing ## CS411P - Grade: 4TH YEAR ### Dr. Reem El-Deeb ### Mansoura University - Faculty of Computers and Information - Department of Computer Science # Natural Language Processing ### Dr. Reem El-Deeb ### Lecture I # What is NLP? - Getting computers to understand everythi...

# Natural Language Processing ## CS411P - Grade: 4TH YEAR ### Dr. Reem El-Deeb ### Mansoura University - Faculty of Computers and Information - Department of Computer Science # Natural Language Processing ### Dr. Reem El-Deeb ### Lecture I # What is NLP? - Getting computers to understand everything we say and write. - Examples of large amount of data, including the number of hours of video, - How much data is processed, and the number of transactions per second. # How it Works - The diagram shows how NLP works. - Starting with unstructured data - Text classification. - Text clustering. - Information retrieval. - Text summarization. # NLP Applications - Spell checking, keyword search, finding synonyms. - Extracting information from websites such as product price, dates, location, - people or company names. - Machine Translation - example of a news report translated into English, and - the different ways the word "Hi" is translated. # Speech to Text (STS) and Text to Speech (TTS) - An example of a command being given to the system. - Data visualization of the F1 coefficient magnitue. - Of female vs male speakers. # NLP Applications - Question Answering - Example of Watson winning Jeopardy against a human # Spam Detection - Diagram showing the process of Spam Detection. - Email is fed to a machine learning model, that outputs whether an email is - Spam or Not. # Sentiment Analysis - Diagram of 8 people with emoticons representing sentiment. # Caption Generation - Example of 3 images with caption. # Natural Language Processing (NLP) - NLP is the subfield of artificial intelligence that uses computational techniques to analyze and synthesize human natural language and speech. - The goal of NLP is to be able to design algorithms to allow computers to understand natural language in order to perform a task. # Why is Natural Language Processing Hard? - Vagueness and imprecision of language. - Redundancy (many ways of saying the same). - Ambiguity (many senses of the same data). - Non-linguistic means of expression (gestures, ...). - Language understanding often requires unsound inference. - Language is dynamic. # NLP Applications - Applications range from simple to complex. - Spell checking, keyword search, finding synonyms. - Extracting information from websites. - Classifying texts. - Sentiment analysis. - Machine translation. - Spoken dialog systems (Chatbots). - Complex question answering. # NLP Applications - Semantic Analysis (What is the meaning of a query statement?). - Co-reference/Anaphora resolution (e.g., What does "he" or "it" refer to in a document?). # NLP Applications - Natural Language Understanding (Linguistics). - Natural Language Generation. - Natural Language Text. - Phonology. - Morphology. - Syntax. - Semantics. - Pragmatics. # Categories of Linguistic Knowledge - Phonology: the study of patterns of speech sounds. e.g., “read” → /r iy d/. - Morphology: how words can be changed by inflection or derivation. - e.g, read, reads, reader, reading. - Syntax: the ordering and structure between words and phrases (i.e. grammar). - e.g, Noun-Phrase → article adjective noun. - Semantics: the study of how meaning is created by words and phrases. - Pragmatics: the study of meaning in contexts. - (Speaker's identity and intent). - Ex: you have a green light. - Discourse: coherent (logical) groups of sentences. # THANKS