There are no pre-requisites for this module to be added

Conversational AI has attracted increasing attention in academia and industry in the past five years. There have been over 100 companies working on voice-AI or Conversational AI-based products, including the world’s most valuable brands (e.g. Apple, Google, Amazon, Huawei, etc.) and start-ups (e.g. Emotech, Alana). On the other hand, there are global competitions organised by Amazon, which focus on state-of-the-art technologies in diverse conversational AI tasks, e.g. social conversation and task-oriented conversation. This module can help students learn about conversational AI, related NLP and ML/DL methodologies, and state-of-the-art research topics. It also can provide students with the experience of team-level project work on realistic human daily problems, which offers a good insight into academic and industrial perspectives. The module covers the following topics: • Data types and formats: numerical and time series, graph, textual, unstructured, • Data sources and interfaces: open data, APIs, social media, web-based • NoSQL databases such as document (MongoDB), graph and key-value pair • Techniques for dealing with large data sets, including Map Reduce • Developing Data-Driven Applications in Python The Benchmark Statement for Computing specifies the range of skills and knowledge that should be incorporated in computing courses. This module encompasses cognitive skills in Computational Thinking, Modelling and Methods and Tools, Requirements Analysis and practical skills in specification, development and testing and the deployment and use of tools and critical evaluation, and providing useful generic skills for employment.

Upon completion of this module you will be able to

LO1: Demonstrate expertise in using Python within an interactive development environment to develop, test, and optimize NLP applications, ensuring efficient and reproducible workflows.

LO2: Critically select and apply appropriate programming constructs and libraries for NLP tasks, including text processing, language understanding, and generation, while making informed decisions on data handling and model integration.

LO3: Design and implement modular, reusable, and well-documented code for NLP pipelines, incorporating robust error handling and performance optimizations to address real-world language processing challenges.

LO4: Critically evaluate the effectiveness of implemented NLP solutions, assessing model performance, scalability, and ethical considerations in language processing applications.