AI + TRANSLATION - 2026/7

Module Overview

The module provides students with advanced knowledge about how Artificial Intelligence (AI) can be used for facilitating multilingual communication. The module explores how Natural Language Processing (NLP) and Machine Translation (MT) facilitate multilingual communication and presents different AI-based paradigms for producing multilingual content. Students gain hands-on experience in how to train translation engines, and how the output of these engines should be evaluated. The role of Large Language Models (LLMs) in workflows that produce multilingual content is also explored. In addition, students use LLMs for processing of multimodal input in order to produce captions for images, audio description for videos and to generate natural-sounding speech. The module enables students to understand the challenges faced when using artificial intelligence for multilingual communication and translation, regardless of whether they are processing text, speech or video. The focus is on enhancing students¿ digital capabilities, especially those linked to the language services industry and multilingual communication workflows. 

Students gain a thorough understanding of the role of data in AI-based multilingual communication workflows by exploring how to use corpora to learn the characteristics of a language, harvest relevant data from the web, annotate it with relevant information, and use it for tuning AI-based tools. Examples of practical tasks in dedicated practical sessions include text classification (e.g. sentiment analysis, harmful text filtering), development of chatbots and fine-tuning of MT engines. These practical tasks aim at improving students¿ problem-solving skills and contribute to their future career development. Knowledge of programming is not necessary, but students who have a programming background are offered the opportunity to use this knowledge during the module. 

While TRAM511 is not a prerequisite, students taking this module are expected to have a good understanding of AI in general.

Module provider

Literature & Languages

Module Leader

ORASAN Constantin (Lit & Langs)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 7

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

None

Module content

Indicative module content:

• How Natural Language Processing and Machine Translation can enable multilingual communication
• Using Large Language Models to address problems from translation and multilingual communication
• Machine Translation paradigms: training MT engines and evaluating MT output
• The role of corpora in multilingual communication: applications and corpus construction
• Large Language Models for multimodal information processing
• Practical NLP applications for multilingual and multimodal communication

Assessment pattern

Alternative Assessment

None

Assessment Strategy

The assessment strategy is designed to:

• Demonstrate knowledge and understanding of the AI-based approaches that can be used in multilingual communication and translation 
• Show how to use existing tools and customise them for specific tasks. 

Thus, the summative assessment for this module consists of:

• An Essay on a Given Topic (40%) 
  (addresses learning outcomes: 1, 3, and 4)
  Students will have to submit an essay on one of the more theoretical topics covered in the first half of the semester. The essay will be due at the middle of the semester. 

Portfolio of Solutions to the Weekly Homework (60%)
(addresses learning outcomes: 2, 3, 4, 5)
Students will be given practical homework every two weeks and will be asked to prepare a portfolio with their answers. In some cases, students will be asked to write "small essays" (250-300 words) discussing a practical topic, whilst in other cases they will need to explain their experience using an AI-based technology. The portfolio can be seen as a diary of the practical activities covered in this module and it is expected to indicate any problems that the students encountered and how they solved them. All the pieces of homework given during the semester will have to be included in the final portfolio, which will be due at the end of the semester. The marking will focus both on the answers to the homework and on the reflective analysis. 

Formative assessment:

Students will receive formative feedback on assignment 1 through practical exercises and discussions in the class in the weeks preceding the submission. Formative feedback for the second assessment will be provided on the first three tasks of the portfolio in the form of group discussions. After these discussions, students will be asked to update their portfolio with reflective analysis of their initial solutions

Feedback: 

Students will be provided with detailed written feedback following coursework assignments. Verbal feedback will also occur in class and individual appointments if required. Exercises comparable to the assessed tasks will be discussed in class throughout the module.

Module aims

• Provide a thorough overview of the basic concepts involved in using AI for multilingual communication and translation
• Demonstrate how Natural Language Processing and Large Language Models can benefit multilingual communication and translation
• Enable the students to demonstrate a thorough understanding of the strengths and weaknesses of automatic processing tools used in multilingual and multimodal communication workflows
• Offer students ample opportunities for hands-on practice with automatic tools used in multilingual communication

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to: allow students to develop theoretical and practical knowledge of how to implement effectively AI in multilingual communication. It will provide students with a good understanding of the practical aspects of using Natural Language Processing and Large Language Models in multilingual communication and translation workflows. It will also provide students with an understanding of the role data plays in these workflows. This is in line with the programme¿s overall aims of enhancing students¿ background in AI-based technologies for translation and multilingual communication.

The learning and teaching methods include:

• Seminars: Weekly seminars sessions will combine lecture-type teaching with practical activities. Both components will be interspersed with opportunities for group and whole-class discussions. In each session, the tutor will introduce theoretical and practical concepts supported by demonstrations of relevant tools to enhance students¿ understanding.
• Captured content: Captured content for each weekly session includes PDF slides and Panopto recordings of the lecture components. This material is designed to support students in developing their understanding of key concepts and theories.
• Guided learning: Students¿ in-class learning is supported by a structured programme of guided activities to complete at home. These include practical exercises, reading relevant literature, and undertaking tasks that complement the work done in class. Students are also encouraged to engage with each other on SurreyLearn.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: TRAM514

Other information

The University of Surrey is committed to developing graduates with strengths in Employability, Digital Capabilities, Global and Cultural Capabilities, Sustainability, and Resourcefulness and Resilience. This module is designed to allow students to develop knowledge, skills, and capabilities in the following areas:

Digital capabilities: Throughout this module students will learn to navigate and utilise a number of AI-based technologies and digital resources. Module assessments will require students to use a range of digital platforms and resources related to translation technology and multilingual communication. This will enhance greatly their Digital Capabilities. 

Resourcefulness and Resilience: The students are expected to engage with online materials and a variety of software. They will learn how and where to access data and code, evaluate their relevance to the problem at hand and how to use them to solve their problems. Students will gain problem-solving skills which will benefit their critical thinking and strongly improve their Resourcefulness and Resilience. 

Employability: This module will improve students¿ Employability by diversifying the employment avenues available to them. The topic covered in this module will prepare the students to take jobs in companies that employ advanced technologies in the translation and multilingual communication processes. The students completing this module will be able to accept a wider range of jobs including such as AI trainers and data scientists. 

Global and cultural capabilities: The module will be taught in an interactive and collaborative way in a class which will represent different nationalities and languages. The topics of the module will enhance students¿ global capabilities implicitly and explicitly. 

Programmes this module appears in

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2026/7 academic year.