Natural Language Processing

COMP34711 Natural Language Processing 10 Semester 1 Undergraduate Level 3 Goran Nenadic Unit coordinator Department of Computer Science 1 FHEQ level (Framework for Higher Education Qualifications) ' Last part of a Bachelors ' European Credit Transfer & Accumulation System Rating : 5.0 This course unit will cover the key linguistic and algorithmic foundations of natural language processing (NLP). It will explore the main challenges in processing textual data, representing word and document semantics, and processing and identifying patterns in speech. It will consider both rule-based and machine/deep learning approaches, and building and using large language models for specific tasks, including applications such text classification, word sense disambiguation, speech synthesis and speech recognition. The syllabus will cover the following topics:  •    Introduction to NLP•    Lexical Semantics  •    Language Models•    Deep Learning for NLP•    Speech Synthesis and Recognition•    NLP Applications•    Ethical Considerations for NLP  This course unit will cover the key linguistic and algorithmic foundations of natural language processing (NLP). It will explore the main challenges in processing textual data, representing word and document semantics, and processing and identifying patterns in speech. It will consider both rule-based and machine/deep learning approaches, and building and using large language models for specific tasks, including applications such text classification, word sense disambiguation, speech synthesis and speech recognition. The syllabus will cover the following topics:  •    Introduction to NLP•    Lexical Semantics  •    Language Models•    Deep Learning for NLP•    Speech Synthesis and Recognition•    NLP Applications•    Ethical Considerations for NLP  This course unit provides an introduction to the area of natural language processing as one of the key areas of artificial intelligence. Enabling computers to process data in 'natural language' (the kind of language that people use to communicate with one another) is becoming more and more important, in particular since large language models have become widely used. The course unit aims to introduce essential components and key applications of natural language processing, and explain the major challenges in processing large-scale, real-world natural language both in its written and spoken forms.  ILO 1: Discuss,  implement and evaluate key NLP tasks and applications, including text classification, word sense disambiguation, entity recognition, speech processing, etc.ILO 2: Explain the use of different approaches including statistical approaches, machine/deep learning techniques in building NLP systems.ILO 3: Discuss the major challenges in processing large-scale, real-world natural language data.ILO 4: Explain how the essential components of NLP systems are built, assessed and modified, including lexical and semantic representations and large language models.ILO 5: Understand the issues involved in deploying and evaluating NLP systems, including ethical and societal challenges. •    Introduction to NLP•    Lexical Semantics  •    Language Models•    Deep Learning for NLP•    Speech Synthesis and Recognition•    NLP Applications•    Ethical Considerations for NLP  Weekly workshops/lectures with structured input and exploratory activities. These will be organised as a blend of brief presentations, hands-on individual and group activities and discussions of materials and tasks that are available online (question-answer sessions). Weekly laboratories will be individual and group hands-on sessions for trying out new systems or techniques (with set tasks, known answers) and will be also used for preparation for course work. These will be used as surgeries to provide feedback on coursework and as an opportunity to ask questions about the set tasks with more open ended/specific discussions and feedback. Coursework will provide design, implement and analysis tasks with real-world data. 1 Written exam 70% 2 Written assignment (inc essay) 30% There will be both face-to-face feedback provided in workshops and tutorial and lab sessions, and written feedback provided through Blackboard discussion forum. COMP24112 Machine Learning Pre-Requisite Compulsory COMP24112 is a pre-requisite but students will be provided with the material from this course if they have not taken it.COMP24112 is a pre-requisite but students will be provided with the material from this course if they have not taken it. N <ol><li>Bird, Steven. (2009). Natural language processing with Python. O'Reilly Media Inc. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9780596555719&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 9780596555719</a>  </li><li>Kamath, Uday. (2019). Deep learning for NLP and speech recognition. Springer. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,3030145964&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 3030145964</a>  </li><li>Jurafsky, Dan. (2009). Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition. Pearson/Prentice Hall. ISBN:<a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9780135041963&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank"> 9780135041963 </a></li></ol> Assessment written exam 2 Lectures 22 Practical classes & workshops 22 0 54