Projektai / Projects

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 135
  • Interviews conducted across the world by police and other law enforcement agencies with suspects, victims and witnesses are crucially important in determining criminal justice outcomes. Several Member countries have developed (or are developing) an ethical approach termed ‘investigative interviewing’ that aims to obtain detailed and reliable information while respecting human rights. This approach is consistent with the 2021 United Nations Declaration of the ‘Principles of Effective Interviewing’. However, law enforcement agencies in most countries remain unaware of the investigative interviewing approach, undertaking unethical practices characterized by guilt presumption and confession orientation that often rely on psychological manipulation, intimidation or physical torture and can lead to miscarriages of justice and failed investigations. This Action involves convening regional and in-country networks of researchers, practitioners, and policymakers working with each other and the Action Team to enable wider implementation of the ‘Mendez Principles’.
  • Multi3Generation aims to foster an interdisciplinary network of research groups working on different aspects of language generation (LG). We frame LG broadly as the set of tasks where the ultimate goal involves generating language. In contrast to the more classical definition of NLG, this also includes tasks not concerned with LG in an immediate sense, but that could obviously inform or improve LG models. The Action will focus on the four core challenges: 1) Data and information representations: in modern applications, inputs can be different sources such as images, videos, KBs and graphs. 2) Machine Learning (ML): modern ML approaches face additional challenges when applied to LG; inputs should be mapped to different correct outputs, i.e. challenges involve e.g. structured prediction and representation learning. 3) Interaction: Applications of LG, e.g. Dialogue Systems, Conversational Search Interfaces and Human-Robot Interaction pose additional challenges to LG due to uncertainty derived from the changing environment and the non-deterministic fashion of interaction. 4) KB exploitation: structured knowledge is key to many NLP tasks, including NLG, supporting ML methods that require expansion, filtering, disambiguation or user adaptation of generated content. This Action aims to address these challenges by answering the following questions: How can we efficiently exploit common-sense, world knowledge and multi-modal information from various inputs such as knowledge bases, images and videos to address LG tasks such as multi-modal machine translation (MT), video description and summarisation? How can modern ML methods such as multi-task learning (MTL), representation learning and structured prediction be leveraged for LG? How can the models from (1) and (2) be exploited to develop dialogue-based, conversational Human-Computer and Human-Robot interaction methods?
  • Effective discourse in any language is characterized by clear relations between sentences and coherent structure. But languages vary in how relations and structure are signalled. While monolingual dictionaries and grammars can characterise the words and sentences of a language and bilingual dictionaries can do the same between languages, there is nothing similar for discourse. For discourse, however, discourse-annotated corpora are becoming available in individual languages. The Action will facilitate European multilingualism by (1) identifying and creating a portal into such resources within Europe – including annotation tools, search tools, and discourse-annotated corpora; (2) delineating the dimensions and properties of discourse annotation across corpora; (3) organising these properties into a sharable taxonomy; (4) encouraging the use of this taxonomy in subsequent discourse annotation and in cross-lingual search and studies of devices that relate and structure discourse; and (5) promoting use of the portal, its resources and sharable taxonomy. With partners from across Europe, TextLink will unify numerous but scattered linguistic resources on discourse structure. With its resources searchable by form and/or meaning and a source of valuable correspondences, TextLink will enhance the experience and performance of human translators, lexicographers, language technology and language learners alike.
  • The COST Action Positive Energy Districts European Network (PED-EU-NET) aims to mobilise researchers and other relevant stakeholders across different domains and sectors to drive the deployment of Positive Energy Districts (PEDs) in Europe through open sharing of knowledge, exchange of ideas, pooling of resources, experimentation of new methods and co-creation of novel solutions.