Teaching Workshop: Machine Translation Literacy
A.Y. 2024/2025
Learning objectives
The module aims to provide trainees with a comprehensive overview of artificial intelligence (AI)-based machine translation (MT) systems such as DeepL, Lara or Google Translate, including Large Language Models (LLM) such as ChatGPT, Gemini or Perplexity AI and their impact on the world of interlingual communication and translation, both professional and non-professional. The opportunities and challenges offered by these technologies for translators and language professionals will be explored.
Expected learning outcomes
At the end of the workshop, students will be able to:
- Understand the evolution of the relationship between translation and technology, including the current deployment of MT and LLM systems, how they are used and their impact on the skills and roles of language professionals.
- Learn about the main types of MT and LLM available, from those freely accessible on the Web to those that can be customised for specific needs.
- Use LLMs for translation-related tasks such as text generation and revision, terminology support, localisation and content simplification.
- Assess the quality of machine translation generated by both traditional MT systems and LLM, using specific criteria and benchmarking methods.
- Apply different modes of post-editing (light and full) and understand the differences from human translation revision.
- Integrate/interact effectively between Computer Assisted Translation (CAT) tools, such as RWS Trados, Phrase or Wordscope, and MT and LLM technologies to optimise workflows.
- Adopt pre-editing and source text adaptation strategies to improve output quality for both MT and LLM, reducing the need for post-editing.
- Develop web content optimised for MT and generated effectively using LLM.
- Understand the training and customisation processes of translation engines and the possibility of using LLM as a basis for specific solutions.
- Analysing the main pricing models for pre-editing, post-editing and translation services with advanced technologies.
- Recognise the ethical and professional limits associated with the use of artificial intelligence in translation, with a focus on issues such as bias, privacy and reliability.
- Understand the evolution of the relationship between translation and technology, including the current deployment of MT and LLM systems, how they are used and their impact on the skills and roles of language professionals.
- Learn about the main types of MT and LLM available, from those freely accessible on the Web to those that can be customised for specific needs.
- Use LLMs for translation-related tasks such as text generation and revision, terminology support, localisation and content simplification.
- Assess the quality of machine translation generated by both traditional MT systems and LLM, using specific criteria and benchmarking methods.
- Apply different modes of post-editing (light and full) and understand the differences from human translation revision.
- Integrate/interact effectively between Computer Assisted Translation (CAT) tools, such as RWS Trados, Phrase or Wordscope, and MT and LLM technologies to optimise workflows.
- Adopt pre-editing and source text adaptation strategies to improve output quality for both MT and LLM, reducing the need for post-editing.
- Develop web content optimised for MT and generated effectively using LLM.
- Understand the training and customisation processes of translation engines and the possibility of using LLM as a basis for specific solutions.
- Analysing the main pricing models for pre-editing, post-editing and translation services with advanced technologies.
- Recognise the ethical and professional limits associated with the use of artificial intelligence in translation, with a focus on issues such as bias, privacy and reliability.
Lesson period: Second semester
Assessment methods: Giudizio di approvazione
Assessment result: superato/non superato
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
Second semester
Course syllabus
The workshop will offer a critical and in-depth analysis of technologies applied to translation, considering both the current debate - often polarised between enthusiasm and distrust - and the practical and ethical implications of their use. The aim is to overcome the opposition between technophiles and technophobes, providing a balanced and evidence-based understanding.
The course will provide an up-to-date overview of translation technologies, exploring in particular:
- The state of the art of Machine Translation (MT) and Computer Assisted Translation (CAT), analysing their potential and limitations.
- The introduction and practical use of large language models (LLM) for text generation, revision and adaptation.
- The applications of MT, CAT and LLM technologies to translate texts of different natures (technical, creative, scientific, popular, etc.).
Students will be actively involved and, through guided exercises, will have the opportunity to
- Experiment with and compare MT, CAT and LLM tools.
- Simulate typical workflows in the translation industry, which integrate MT, CAT and LLM to optimise the translation process.
- Analysing realistic scenarios considering the evolution of the skills required of language professionals.
The course will provide an up-to-date overview of translation technologies, exploring in particular:
- The state of the art of Machine Translation (MT) and Computer Assisted Translation (CAT), analysing their potential and limitations.
- The introduction and practical use of large language models (LLM) for text generation, revision and adaptation.
- The applications of MT, CAT and LLM technologies to translate texts of different natures (technical, creative, scientific, popular, etc.).
Students will be actively involved and, through guided exercises, will have the opportunity to
- Experiment with and compare MT, CAT and LLM tools.
- Simulate typical workflows in the translation industry, which integrate MT, CAT and LLM to optimise the translation process.
- Analysing realistic scenarios considering the evolution of the skills required of language professionals.
Prerequisites for admission
None
Teaching methods
Blended lessons.
The course includes theoretical lectures, practical demonstrations with MT and LLM tools, laboratory exercises and case studies. The critical use of technologies and an in-depth reflection on the impact of their use in the translation world will be encouraged.
The course includes theoretical lectures, practical demonstrations with MT and LLM tools, laboratory exercises and case studies. The critical use of technologies and an in-depth reflection on the impact of their use in the translation world will be encouraged.
Teaching Resources
Reference materials will be provided during the course.
Assessment methods and Criteria
The workshop includes in-progress verification activities and a final verification with in-class correction and general feedback.
Professor(s)