SMART TECHNOLOGIES FOR TRANSLATION - 2024/5

Module code: TRAM502

Module Overview

Students taking this module explore the main theoretical and practical aspects of smart technologies for translation, with emphasis on how the latest developments in Natural Language Processing, Large Language Models (e.g. ChatGPT) and Corpus Linguistics can to help translators. The purpose of this module is to enable students to understand the challenges faced when using computers artificial intelligence to process text automatically or when they need to process speech as an input. The focus is on enhancing students’ digital capabilities, especially those linked to the translation industry. The module will provide students with knowledge about the fields of Machine Translation (MT), Natural Language Processing (NLP), Large Language Models (LLMs) and Corpus Linguistics (CL). 
 
The module will start with an introduction to NLP and machine translation and will present different paradigms to produce automatic translations. Students will be provided with hands-on experience on how to train translation engines, and how it is possible to evaluate MT, as well as how to use LLMs for translation related tasks. . Other topics such as terminology extraction, speech recognition and translation will also be covered. The students will learn how to harvest relevant corpora from the web, clean them and use them for translation-related tasks.The practical tasks addressed in the module will improve students’ problem-solving skills and contribute to their future career development. 
 
Knowledge of programming will not be necessary, but students who have a programming background will be given the opportunity to use this knowledge in the module. Links will be established with other modules such as TRAM500 and TRAM496.

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

Overall student workload

Independent Learning Hours: 106

Seminar Hours: 22

Guided Learning: 11

Captured Content: 11

Module Availability

Semester 2

Prerequisites / Co-requisites

None

Module content

Indicative module content:


  • Introduction to Natural Language Processing (NLP) and Machine Translation (MT) 

  • Using Large Language Models like ChatGPT to solve translation related problems 

  • Existing paradigms in MT, how to train an MT engine and how to evaluate MT 

  • Building corpora from the Web using data scraping and cleaning of files 

  • Building parallel corpora and automatic alignment of corpora 

  • Terminology extraction 


Assessment pattern

Assessment type Unit of assessment Weighting
Coursework An essay on a given topic (1,000-1,200 words) 40
Practical based assessment Portfolio containing solutions to exercises given during the semester 60

Alternative Assessment

n/a

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate:

* knowledge and understanding of the approaches used in the area of smart technologies for translation
* knowledge of how to use existing tools and develop simple programs to help them achieve their tasks.
 

Thus, the summative assessment for this module consists of:


  • An Essay on a Given Topic (1,000 - 1,200 words) (40%)
    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 f Solutions to the Weekly Homework (60%)
    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 a smart technology. The portfolio can be seen as 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. Part of the workshops will be used to discuss the solution for the homework given in the first half of the module. After these discussions, students will be asked to update their portfolio with reflective analysis of their initial solutions. 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

Formative assessment will focus on student participation and class discussions throughout the module.

The students will be able to discuss their solutions to the homework before submitting the revised portfolio.


Feedback

Students will be provided with detailed written feedback following coursework assignments. Verbal feedback will also occur in class and individual appointments if required.

Module aims

  • The module aims to: provide a thorough overview of the basic concepts involved in using smart technologies for translation
  • Demonstrate how Large Language Models can benefit translators
  • give students the ability to understand the strengths and weaknesses of automatic processing tools in translation workflows, including hybrid workflows which include speech recognition
  • provide students with a sound understanding of the relevant methodologies
  • enable students to select suitable NLP, CL and MT tools for their needs

Learning outcomes

Attributes Developed
001 By the end of the module students will be able to: demonstrate an in-depth knowledge base of specific topics within the area of smart technologies for translation KC
002 Demonstrate practical skills in using a wide variety of state-of-the-art tools and resources relevant to NLP, CL, and MT KCP
003 Demonstrate a critical understanding of the published literature and current debates in these areas KCT
004 Demonstrate ability to communicate findings in writing PT
005 Appreciate new societal, technological and language-industry demands CP

Attributes Developed

C - Cognitive/analytical

K - Subject knowledge

T - Transferable skills

P - Professional/Practical skills

Methods of Teaching / Learning

The learning and teaching strategy is designed to provide students with a good understanding of the practical aspects of using NLP and CL in translation workflows towards a smarter use of technologies in translation. This is in line with the MA in Translation’s overall aims of enhancing students’ background in technologies for translation

The learning and teaching methods include:


  • Workshops will be interspersed with opportunities for group and whole class discussions

  • Contact hours will be complemented with materials for and activities for guided study posted on SurreyLearn



Self-study

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: TRAM502

Other information

Surrey's Curriculum Framework 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:

Throughout this module students will learn to navigate and utilise a number of smart technologies, digital resources and online databases to aid their learning. Module assessments will require students to use a range of digital platforms and resources related to translation technology. This will enhance greatly their Digital Capabilities. 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.

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 process. Even if the students choose to be freelance translators, they will be able to accept a wider range of jobs as they are able to rely on a variety of technologies highly pertinent to the real world translation environment outside of University .

The module will be taught in an interactive and collaborative way in a class which will represent different nationalities and languages. The topics addressed in this module will be beneficial to other modules such as TRAM496 as well as the topic-based dissertations.

Programmes this module appears in

Programme Semester Classification Qualifying conditions
Translation and AI (Chinese Pathway) MA 2 Optional A weighted aggregate mark of 50% is required to pass the module
Translation MA 2 Optional A weighted aggregate mark of 50% is required to pass the module
Translation and Interpreting MA 2 Optional A weighted aggregate mark of 50% is required to pass the module
Translation and Interpreting Studies MRes 2 Optional A weighted aggregate mark of 50% is required to pass the module

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 2024/5 academic year.