Nowadays any communication barrier is detrimental to society. This project will research and develop the SignON communication service that uses machine translation to translate between Sign and spoken languages. This service will facilitate the exchange of information among deaf and hard of hearing, and hearing individuals. In this user-centric and community-driven project we will tightly collaborate with European deaf and hard of hearing communities to (re)define use-cases, co-design and co-develop the SignON service and application, assess the quality and validate their acceptance. Our ultimate objective is the fair, unbiased and inclusive spread of information and digital content in European society. Our project will develop a free, open application and framework for conversion between video (capturing and understanding Sign language), audio and text and translation between Sign and spoken languages. To facilitate these tasks we propose a common representation for mapping of video, audio and text into a unified space, that will be used for translating into the target modality and language. To ensure wide uptake, improved sign language detection and synthesis, as well as multilingual speech processing on mobile devices for everyone, we will deploy the SignON service as a smart phone application running on standard modern devices. We envisage the application as a light-weight interface. The SignON framework, however, will be distributed on the cloud where the computationally intensive tasks will be executed.The project will be driven by a focused set of use-cases tailored towards the deaf communities. We target the Irish, British, Dutch, Flemish and Spanish Sign and English, Irish, Dutch, Spanish spoken languages. However, SignON will incorporate sophisticated machine learning capabilities that will allow (i) learning new Sign, written and spoken languages; (ii) style-, domain- and user-adaptation and (iii) automatic error correction, based on user feedback
The project proposes to integrate, extend and harmonise national and regional efforts in the field of lexicography, both modern and historical, with the goal of creating a sustainable infrastructure which will (1) enable efficient access to high quality lexical data in the digital age, and (2) bridge the gap between more advanced and lesser-resourced scholarly communities working on lexicographic resources. The need for such an infrastructure has clearly emerged out of the lexicographic community within the European Network of e-Lexicography COST Action which will end in 2017. Current lexicographic resources, both modern and historical, have different levels of structuring and are not equally suitable for application in other fields, e.g. Natural Language Processing. The project will develop strategies, tools and standards for extracting, structuring and linking lexicographic resources to unlock their full potential for Linked Open Data and the Semantic Web, as well as in the context of digital humanities. The project will help researchers create, access, share, link, analyse, and interpret heterogeneous lexicographic data across national borders, paving the way for ambitious, transnational, data-driven advancements in the field, while significantly reducing a duplication of effort across disciplinary boundaries. ELEXIS will be carried out by a balanced consortium with distributed geographical origins. It is composed of content-holding institutions and researchers with complementary backgrounds - lexicography, digital humanities, language technology and standardisation - a crucial feature required to address the multi-disciplinary objectives of the project. In cooperation with CLARIN and DARIAH, it will focus on defining and providing common interoperability standards, workflows, conceptual models and data services as well as training and education activities focusing on user needs and cross-disciplinary fertilisations.