SignON aims to reduce the communication gap between the deaf, hard of hearing and hearing communities. We bring together the experience and know-how of deaf and hard of hearing communities with multidisciplinary academic and industry expertise. A team of experts from different backgrounds will develop the SignON communication service which will focus on the translation between sign and oral languages.

The SignON consortium brings together a wide-ranging and complementary set of skills and expertise. Our consortium includes members who represent and/or work closely with deaf communities (EUD, VGTC, DCU, KU Leuven and TCD); sign linguistics (KU Leuven, TCD, DCU, TU Dublin), exploitation, innovation and design (MAC, VRT and FINCONS); natural language processing, infrastructure and policies (TU Dublin, NTU, UPF, INT and KU Leuven); machine translation and quality estimation (UPV/EHU, KU Leuven, TiU); sign language recognition (UGent and UCD); 3D animation and avatar synthesis (TU Dublin and UPF/GTI group); automated speech recognition (RU).

For more information, visit signon-project.eu

With the increase in MT quality over the last years, it has now become a common practice to integrate MT in the workflow of language service providers (LSPs) and other actors in the translation industry. With MT having a direct impact on the translation workflow, it is important not only to use high-quality MT systems, but also to understand the quality dimension so that the humans involved in the translation workflow can make informed decisions. The evaluation and monitoring of MT output quality has become one of the essential aspects of language technology management in LSPs' workflows.

This 6-month project was a collaboration between Tilburg University and Orbital14, an Aglatech14 company with the overall objective of developing a machine translation quality assessment (MTQA) tool that simplifies the quality assessment of MT engines, combining quality evaluation and quality estimation on document and sentence level and is tailored towards language service providers.

Take a look at our paper https://aclanthology.org/2022.eamt-1.43/

The corpus contains 297 hotel reviews in written English (21.464 words), translated into written Dutch (22.274 words) and into NGT videos (230,54 minutes). It is publicly available through the ELG and the CLARIN platforms.

This ongoing project will lead to the creation of a parallel corpus of semi-spontaneous VGT (source language) and written Dutch (target language). All VGT videos included were orignally produced by authentic signers for a signing audience.