Modules

Core Module Information
Module title: Machine Learning for Conversational AI
SCQF level: 10:
SCQF credit value: 20.00
ECTS credit value: 10
Module code: SET10120
Module leader: Yanchao Yu
School School of Computing, Engineering and the Built Environment
Subject area group: Computer Science
Prerequisites

Requisites: Pre-requisite: Python Programming Experinece
Description of module content:

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.
Learning Outcomes for module:

Upon completion of this module you will be able to

LO1: Critically evaluate the tools and techniques of Conversational AI, i.e. language understanding and generation, dialogue management, and multimodal interaction.

LO2: Select and apply a range of specialised data, tools and techniques for Conversational AI, i.e. language understanding and generation, dialogue management, and multimodal interaction.

LO3: Experiment with specialised techniques for complex real-world problems, such as Natural Language Processing and machine learning.

LO4: Design, develop, and critically evaluate data-driven conversational applications
Full Details of Teaching and Assessment
2026/7, Trimester 2, In Person,
VIEW FULL DETAILS
Occurrence: 001
Primary mode of delivery: In Person
Location of delivery: MERCHISTON
Partner:
Member of staff responsible for delivering module: Yanchao Yu
Module Organiser:


Student Activity (Notional Equivalent Study Hours (NESH))
Mode of activityLearning & Teaching ActivityNESH (Study Hours)NESH Description
Face To Face Guided independent study 140 Students will work by themselves through all provided materials and their research topic till the end of the teaching period.
Face To Face Lecture 20 2 hours lecture content with focusing on technique, concepts and other related tools.
Face To Face Practical classes and workshops 30 Students will spend 2 hrs per week to get practice on their techniques and explore the group project ideas.
Independent Learning Project Supervision 10 from week 3, students will start working on their research project under supervision from one of the teaching members till the week after teaching weeks.
Total Study Hours200
Expected Total Study Hours for Module200


Assessment
Type of Assessment Weighting % LOs covered Week due Length in Hours/Words Description
Project - Practical 30 1~2 Week 6 HOURS= 1000 words Coursework 1 requires an individual proposal based on the student's role in the group project (Coursework 2) (e.g., NLU, NLG, DM, CV). The student will be requested to do a short literature review and plan the methodology based on the project requirement. Tutors' feedback will be applied to help students improve their plans, which will directly contribute to their coursework two results. This coursework will help students understand existing technologies and learn how to choose and evaluate their methods for a practical project. An element of this coursework will be submitted around week 7 to give feedback (30%: LOs 1, 2)
Project - Written 50 1~2~3~4 Exam Period , WORDS= 6 pages In coursework two, students will be allocated to different project groups (4-5 members per group). Each project group will work on different academic/industrial projects with detailed requirements. The teaching team will define the general project topic, but each project group will develop the details. At the start of the module, group members will discuss the project direction and define each member's role. Each group will meet weekly with one of the teaching team's supervisors to discuss progress and issues. By the end of the module, Coursework Two will submit a group paper (4-page academic paper, excluding references and appendices)
Oral Presentation 20 1~2~3~4 Exam Period HOURS= 20 mins slides Each group will give a 20-minute oral presentation, followed by Q&A.
Component 1 subtotal: 30
Component 2 subtotal: 70
Module subtotal: 100

Indicative References and Reading List - URL:
SET10120/SET11124 Machine Learning for Conversational AI
 

Related information