This project investigates how machine translation services can help employees from administrations, NGOs and education to communicate with refugees. Providing public services to newly arrived refugees is a linguistic challenge: interprets are expensive and not available for all languages. Although machine ...

We investigate if and how the quality of video subtitles generated by AI-based technology (i.e. transcription and machine translation of spoken language) can be scored automatically.

The project consists in developing a prototype for a ZHAW neural machine translation system trained on academic texts. Freely accessible systems such as DeepL and Google Translate are not specifically trained on scientific texts and therefore often present issues regarding terminology, text cohesion, pragmatics and ...

Writing in most contexts today is done with digital, computer-assisted support. Technologies based on artificial intelligence (AI) such as intelligent tutoring (IT), automated writing evaluation (AWE) and machine translation (MT) present new opportunities, perspectives, and risks for tertiary education. The ...

Objectives This project investigates the potential of neural machine translation (NMT) for academic texts (abstracts, papers...) for publication purposes. Initial situation and hypothesis Well-known issues with neural machine translation are text cohesion, (terminology) and "hedging" (hedge terms). This could, ...