Projects Human-Machine Communication

The Computational Competences for Non-Tech Students project is a sub-project of the swissuniversities project digibasics.

Digilinguo is a platform that promotes sustainable practices in the use of digital translation and language tools, thus allowing for language barriers to be overcome in public institutions. Three channels will be created to help it in achieving this objective: / a test track for trying out and…

The aim of the collaboration between Tecom and ZHAW is to create a scientifically sound questionnaire and interviews in order to gain insights into the current industry key figures and the degree of digitalization of technical communication in Switzerland and to publish the results in a publication.

In collaboration with the digital health start-up Adamcares, the ZHAW Usability Lab is investigating the user-friendliness and acceptance of a voice-based documentation for nurses, powered by an AI. The goal is to see if and how the integration on a smartphone or tablet immediately reduces the…

This project, which takes the form of a preliminary study, is working to define the framework conditions for a research project that will be dedicated to exploring the potential offered by so-called speech-to-speech translation (S2ST) for verbal communication between foreign-language nursing staff…

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…

Numbers, technical terms and proper nouns are typical stumbling blocks for simultaneous interpreters. This pilot study investigated conference interpreters' experiences when translation suggestions are displayed on augmented reality glasses (AR).

Evaluation of e-accessibility with usability testing

Automatic Quality Evaluation

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…

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), automated text production (ATP) and machine translation (MT) present new opportunities,…

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

English has become the first truly global lingua franca. Even in multilingual Switzerland, English as a lingua franca (ELF) is replacing the four Swiss languages not only in international but also in intra-national communication. What appears at first glance to be a practical solution to…

Informed Consent and Comprehensibility Issues Research involving humans as subjects can be problematic from an ethical standpoint, because people’s welfare and personal sphere should be protected. For this reason, legislation regulates that potential participants must be informed about research…

Like many other knowledge workers, professional translators spend much of their day making decisions at a computer: reading texts in one language, searching for background information in many languages, referring to terminology databanks to ensure consistency and appropriacy of lexical choices,…