TINE – Translation is Not Enough: Plain Language Adaptation of Multilingual Science

Project factsheet

Consortium

• Universitat Pompeu Fabra, Barcelona, Spain (project management: Horacio Saggion)
• Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland
• Manchester Metropolitan University, Manchester, United Kingdom
• Cardiff University, Cardiff, United Kingdom
• University of Zurich, Zurich, Switzerland

The project is funded by CHIST-ERA through EPSRC (United Kingdom), Agencia Estatal de Investigación (Spain), National Science Centre (Poland) and Swiss National Science Foundation (Switzerland).

Project summary

Open Science mandates exist across Europe indicating that science must be made accessible beyond the borders of academia affecting publishers and scientists alike. However, simply sharing science as publicly available does not make it accessible. Scientists are constrained to write in the languages accepted by major publication venues and the languages of reviewers. Science communication written in a mother tongue is accessible only to a home audience, limiting international impact. Science communication requires accessibility to build impact. If the output of translation is complex technical language we only overcome one accessibility barrier, but many more remain. Translation is not enough. We need simple, clear and accessible cross-lingual science communication. The goal of the TINE project is to enable both producers and lay readers of science communication to access clear scientific information in their own language, promoting multilingualism.

Project objectives

1. Develop state-of-the-art methods for whole-document translation and domain adaptation.
2. Democratisation of access to scholarly documents to enable end-users to consume science without barriers.
3. Decode scientific terminologies and style to fit the needs of lay science consumers.
4. Demonstrate to user communities the practical use of the developed technology.

Use cases

The project is structured around four use cases, which will drive technological requirements for the development of accessible scientific machine translation technology.

• Use Case 1: Accessing Pan-European Grant Databases (Spain). In collaboration with SIRIS Academic, this task will implement a solution to explore international research databases, translating project descriptions and evaluating the usefulness of concept explanations for expert readers.
• Use Case 2: Translating Scientific Papers in Polish for Peer Review (Poland). This task, led by IPI PAN, will enable wider access to Polish-language papers, increasing reviewer diversity in a scientific journal and improving both the quality of peer review and the visibility of Polish science.
• Use Case 3: Improving Accessibility for Welsh-Speaking Communities in Social Care Research (Wales). This task creates accurate, culturally relevant Welsh-language translations of research materials for social care workers, ensuring clarity, accessibility, and alignment with regional dialects for Welsh-speaking service users.
• Use Case 4: Supporting Chinese Students in UK Scientific Degrees (United Kingdom). This task embeds accessible English-to-Chinese translation of science-specific academic materials, enhancing student understanding and evaluating the impact on academic outcomes in collaboration with Hubei University.