Natural Language Understanding

COMP34812 Natural Language Understanding 10 Semester 2 Undergraduate Level 3 Riza Batista-Navarro 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 Drawing from concepts covered in the prerequisite COMP34711: Natural Language Processing unit, this unit will enable students to look more deeply into how machines analyse and recognise meaning expressed in natural language. In this unit, students will gain hands-on experience in investigating solutions to a number of natural language understanding tasks. This will provide students with the know-how required to develop technologies for real-world applications enabling communication between humans and machines, which have become increasingly ubiquitous and indispensable. Drawing from concepts covered in the prerequisite COMP34711: Natural Language Processing unit, this unit will enable students to look more deeply into how machines analyse and recognise meaning expressed in natural language. In this unit, students will gain hands-on experience in investigating solutions to a number of natural language understanding tasks. This will provide students with the know-how required to develop technologies for real-world applications enabling communication between humans and machines, which have become increasingly ubiquitous and indispensable. The unit aims to:  - introduce students to the concepts and computational methods that enable machines to understand and interpret natural language  -  explain the various tasks that underpin natural language understanding, and provide an overview of the state-of-the-art solutions to these tasks as well as their real-world applications ILO 1: To discuss the formulation of different natural language understanding tasks as sequence processing tasks e.g., sequence classification, sequence-to-sequence translation and sequence labelling.ILO 2: To differentiate between different types of parsing algorithms and apply them to natural language data to produce meaning representations.ILO 3: To compare different approaches to tasks such as named entity recognition and sentiment analysis.ILO 4: To relate natural language understanding tasks to applications such as question answering and conversational agents, among others.ILO 5: To develop a solution to a natural language understanding task with application to a real-world problem Analytical skills Problem solving Written communication <ul><li>Introduction to NLU; Task formulations and applications</li><li>Meaning representations: symbolic parsing and logical representations of sentences Vector-based representations (contextualised embeddings)</li><li>Neural networks and neural language models</li><li>Evaluation of models</li><li>Sequence classification and textual entailment (and applications)</li><li>Sequence labelling (and applications)</li><li>Machine reading comprehension (and applications)</li><li>Sequence-to-sequence translation (and applications)</li><li>Limits and weaknesses of state-of-the-art approaches to NLU</li></ul> Asynchronous lectures (weekly)Synchronous workshops (weekly)Labs (fortnightly) 1 Written exam 50% 8 Practical skills assessment 50% Discussions and live coding during workshops (weekly)Labs to support coursework (fortnightly)Cohort-level feedback on exam COMP34711 Natural Language Processing Pre-Requisite Compulsory COMP34812 has a co-requisite of COMP34711 N A Survey of the Usages of Deep Learning for Natural Language Processing    Daniel W. Otter, Julian R. Medina and Jugal K. Kalita    IEEE Transactions on Neural Networks and Learning Systems        DOI: <a href="https://doi.org/10.1109/TNNLS.2020.2979670" target="_blank">10.1109/TNNLS.2020.2979670</a>An introduction to Deep Learning in Natural Language Processing: Models, techniques, and tools    Ivano Lauriola, Alberto Lavelli and Fabio Aiolli    Neurocomputing    DOI: <a href="https://doi.org/10.1016/j.neucom.2021.05.103" target="_blank">10.1016/j.neucom.2021.05.103</a>Natural Language Processing Advancements By Deep Learning: A Survey    Amirsina Torfi, Rouzbeh A. Shirvani, Yaser Keneshloo, Nader Tavaf and Edward A. Fox    Speech and Language Processing    Daniel Jurafsky & James H. Martin    The handbook of computational linguistics and natural language processing     Clark, Alexander,; Fox, Chris,; Lappin, Shalom,    Wiley-Blackwell    2013    ISBN: <a href="https://www.librarysearch.manchester.ac.uk/discovery/search?query=isbn,contains,9781118448670&search_scope=MyInst_and_CI&sortby=rank&vid=44MAN_INST:MU_NUI&lang=en&mode=advanced&offset=0" target="_blank">9781118448670</a>Automatic text summarization: A comprehensive survey    Wafaa S. El-Kassas, Cherif R. Salama, Ahmed A. Rafea, Hoda K. Mohamed    Expert Systems with Applications      DOI: <a href="https://doi.org/10.1016/j.eswa.2020.113679" target="_blank">10.1016/j.eswa.2020.113679</a> Lectures 20 Practical classes & workshops 10 0 70