GLOBALISE: NWO Groot 2021 (2021-2026)
Co-applicant of the Globalise-project to disclose the UNESCO archive with more than 25 million pages of historical records by the VOC. CLTL will deliver the language technology to enrich the archive by detecting expressions for names of persons, organisations, ships and places but also the events that took place in the colonial regions in the Far East. Next, these expressions are mapped to specific identities: who, what, where and when, to generate a Knowledge Graph that represents the history as reported in the letters of the archive.In addition to the recording of these reported facts, we keep track of the sources of the information which will inform us about their perspectives on the events, people and organisations. Our language technology builds on the reading machines that were developed previously in the BiographyNet and Newsreader projects and more recently adapted to the old-Dutch in the CLARIAH-plus project (PhD Stella Verkijk).
A-PROOF: Automated Prediction of post-COVID-19 RecOvery Of Functioning: (2021-2024)
Co-applicant of A-Proof, where the aim is to evaluate effectiveness and costs of allied healthcare in patients recovering from COVID-19. Since there is no control group it will not be possible to directly assess effectiveness. We will therefore obtain estimates of effectiveness through several research questions using different data sources. Research questions focus on outcomes in physical, nutritional, cognitive, mental and daily functioning of patients with COVID-19 who received allied healthcare during recovery; costs of different mono- and multidisciplinary allied healthcare trajectories; and experiences of patients, allied health professionals (AHPs) and referring physicians.
DReaMS LAB (Dialogues, REAsoning and Multi-linguality for Search Lab) / HUAWEI: (2021-2025)
Co-applicant with Maarten de Rijke and Frank van Harmelen, together with the Huawei Consumer Business Group of the DReaMS lab, a new 9-person strong collaboration on intelligent, multi-lingual conversational Multimodal Dialogue Search Systems, focusing on three main approaches: Dialogues, REAsoning and Multi-linguality for Search (Phd’s: Wende Tufa, Stefan Schouten, Baran Barbarestani).
Hybrid Intelligence (HI): augmenting human intellect: NWO Zwaartekracht (2019-2029)
Principal investigator of the Gravitation Project Hybrid Intelligence (HI) that combines human and artificial intelligence. Six Dutch universities will develop theories and methods for intelligent systems that cooperate with humans, that adapt to dynamic circumstances and that can explain their actions. Ethical and legal values, such as transparency, accountability and trust, will be taken into account during the design of such HI systems. We will demonstrate applications of HI systems in healthcare, education and science to show the potential of artificial intelligence to amplify human intelligence instead of replacing it.
- Roles in Hybrid Intelligence:
- PI, Executive Board, Research Line leader of Explainable HI, project leader in Collaborative HI
- Hybrid Intelligence Research Lines: Explainable HI, Collaborative HI
- More info: Gravity Project description
Mining texts for perspectives in human-machine deliberation: Hybrid Intelligence (HI)03: augmenting human intellect NWO Zwaartekracht (2020-2024)
Perspectives in deliberation is about developing Artificial Intelligence techniques to find the underlying structures of debates and group deliberations with the idea that we can help participants to a debate / deliberation to understand why others have a different opinion in this debate. To this end we want to use computational linguistics to extract what we call micro-propositions from text: proposition mining. Secondly, we want to model the implications for stakeholders of these propositions: implication mining. Thirdly, we want to extract and understand the perspectives of the stakeholders on these implications: perspective mining. In addition to understanding the debate and the perspectives, the AI you develop will seek to interact with stakeholders about the interpretations of what they brought in as statements and arguments (PhD: Michiel van der Meer).
Trust as a relationship between social agents in a multimodal world: Spinoza-prize ULM-project 5 associated with : Hybrid Intelligence (HI) 32: augmenting human intellect NWO Zwaartekracht (2020-2024)
Study of trust as a relationship between social agents in a multimodal world that involves multifaceted skills and complex contexts. This work aims to create and evaluate a computational model of trust, from the robot perspective towards trusting humans in collaborative tasks (PhD: Selene Baez).
The role of explainability in task-oriented Human – Robot collaboration within multi-modal context: Spinoza-prize ULM-project 5 associated with : Hybrid Intelligence (HI) 33: augmenting human intellect NWO Zwaartekracht (2020-2024)
What if the Knowledge Graph does not have a simple answer? How to formulate a complex answer that is still useful. We do not take a simple no for an answer. An intelligent agent should explain what it does know and how it is related. A secondary question is that the status of the answer is questionable: uncertainty of a source, how knowledgeable is the source, how much is it shared, is it also denied, how recent is the knowledge, how connected is the knowledge. How can an answer be generated in natural language that is correct, informative, and effective? (PhD: Lea Krause).
Ondersteunen van klinische beslissingen in de revalidatie van patiënten met Covid-19 m.b.v. datascience/textmining: Corona Research Fonds (2020-2022)
Project Partner op gebied van textming waarbij in samenwerking met een aantal partners geprobeerd wordt of we op basis van tekst in Elektronische Patiënten Dossiers (EPD’s) het functionele herstel van COVID-19 patiënten kunnen herkennen en voorspellen en zicht kunnen krijgen op factoren die bijdragen aan het functionele herstel van COVID-19 patiënten tijdens en na ziekenhuisopname, met behulp van text mining technologie en data science. CLTL gaat classificatie-software ontwikkelen die relevante revalidatie-uitkomsten (gebaseerd op de International Classification of Functioning, disability and health (ICF)) aan EPD teksten kan koppelen door deze automatisch te “lezen”. Deze inzichten kunnen de klinische beslissingen tijdens het revalidatietraject ondersteunen.
Communicating with and Relating to Social Robots: Alice Meets Leolani’ – Alani: NWO Open Competitie voor Digitalisering SGW 2019 (2020-2024)
Principal investigator of Alani where we study how social communication and relationships between robots and humans develop as two sides of the same coin: bonding results in better communication and better communication results in better socio-affective bonding. We propose a theoretical framework integrating both perspectives that guides the development of different robot scenarios that will be empirically tested in different user groups. We combine the Theory of Affective Bonding from a social sciences perspective with the Theory of Identity, Reference and Perspective from a linguistics perspective to optimally program social robots for communicative purposes. Likewise, a multi-method approach integrates qualitative and quantitative research designs, for short- and long-term studies both in the field and in the lab. Furthermore, the research combines and extends the results of two previously developed systems for the robots Alice and Leolani, resulting in a merged novel system Alani. (Phd’s: Jaap Kruijt & Peggy van Minkele).
Make Robots Talk and Think: Spinoza-prize ULM-project 5 (2020-2024)
Principal investigator of the Spinoza-project Understanding-Language-By-Machines has funded a follow-up project on “Make Robots talk and think”. Leolani uses communication to learn about us and the world but she also needs to learn our language at the same time. Communicating and reasoning over the physical world and the people she encounters is a real challenge.
Dutch Framenet: Framing situations in the Dutch Language: NWO Vrije Competitie Geesteswetenschappen (2019-2023)
Principal investigator of Dutch Framenet where the project’s objectives are 1) to create a unique data set where similar situations are framed by many different sources and texts using a newly developed data-to-text method, 2) to capture the variation in framing these situations in Dutch and other languages, 3) to capture semantic-pragmatic factors underlying the usage of different frames for similar situations, and 4) to develop semantic frame and role annotation software. An additional concrete outcome of this project is a Dutch FrameNet contributing to the renowned Berkeley Multilingual FrameNet project, which assesses the cross-linguistic validity of frames and investigates crosslinguistic variation in framing. The insights, resources and technologies created by this project provide new possibilities for (industrial) data analysts and researchers from the Humanities and Social Sciences (PhD: Levi Remijnse).
Make Robots Talk: Vossen Spinoza price project: SPI 30-673 (2018-2022)
Principal investigator where CLTL bought a pepper-robot called Leolani with the goal to plug in our natural language processing technology so that the robot can respond to people in an intelligent way and turns into a wise bot. Our robot learns through communication and stores the result in a “brain”. She uses her brain to communicate better and more efficient and to understand situations she encounters. Ultimately, we develop robots that adapt to situations and to you, so that communication and collaboration are more smooth and efficient, with less errors.
Understanding of Language by Machines – an escape from the world of language – “Spinoza-price projects Vossen: SPI 30-673 (2014-2020)The goal of the Spinoza project “Understanding of language by machines” (ULM) is to develop computer models that can assign deeper meaning to language that approximates human understanding and to use these models to automatically read and understand text. Current approaches to natural language understanding consider language as a closed-world of relations between words. Words and text are however highly ambiguous and vague. People do not notice this ambiguity when using language within their social communicative context. This project tries to get a better understanding of the scope and complexity of this ambiguity and how to model the social communicative contexts to help resolving it. The project is divided into 4 subprojects, each investigating a different aspect of assigning meaning:
- ULM-1: The borders of ambiguity: ULM-1 will explore the closed world of language as a system of word relations. The goal is to more properly define the problem and find the optimal solution given the vast volumes of textual data that are available. This project starts from the results obtained in the DutchSemCor project. (Phd Marten Postma).
- ULM-2: Word, concept, perception and brain: ULM-2 will cross the borders of language and relate words and their meanings to perceptual data and brain activation patterns (Phd Emiel van Miltenburg).
- ULM-3: Stories and world views as a key to understanding language: ULM-3 will consider the interpretation of text built up from words as a function of our ways of interacting with the changing world around us. We interpret changes from our world-views on the here and now and the future. Furthermore, we structure these changes as stories along explanatory motivations. This project builds on the results of the European project NewsReader. (PhD Chantal van Son).
- ULM-4: A quantum model of text understanding: ULM-4 is a technical project that investigates a new model of natural-language-processing. Current approaches are based on a pipeline architecture, in which the complete problem is divided in a series of smaller isolated tasks, e.g. tokenization, part-of-speech-tagging, lemmatisation, syntactic parsing, recognition of entities, detection of word meanings. In this new model, none of these tasks is decisive and the final interpretation is left to higher-order semantic and contextual models. This project also builds on the findings of previous European (KYOTO) and ongoing OpeNER and NewsReader and national (BiographyNet) projects carried out at the VU University Amsterdam. The goal is to develop a new model of natural-language-processing in which text is interpreted in a combined top-down and bottom-up proces (PhD’s Filip Ilievski and Minh Lê).
CLARIAH-PLUS: Nationale roadmap grootschalige onderzoeksfaciliteiten NWO (2019-2024)
Member of the Kernteam and Technical Officer.
OpenSourceWordnet: grant Taalunie (2013-2014) and ongoing
Global WordNet Grid: a GWA Project (2006-ongoing)
In 2006 Vossen launched the Global Wordnet Grid: the building of a complete free worldwide wordnet grid. This grid will be build around a shared set of concepts, such as the Common Base Concepts used in many wordnet projects. These concepts will be expressed in terms of Wordnet synsets and SUMO definitions. People from all language communities are invited to upload synsets from their language to the Grid. Gradually, the Grid will then be represented by all languages. The Grid will be available to everybody and will be distributed completely free.
Global Wordnet Association (2000-ongoing)Vossen is Founder and President of the Global WordNet Association. He founded GWA (with Christiane Fellbaum of Princeton University) in 2000 as a public and non-commercial organization that provides a platform for discussing, sharing and connecting wordnets for all languages in the world. For more information see:
- Global Wordnet Association
- 12th Global WordNet Conference 2023, San Sebastian, Spain, January 23-27, 2023
- 11th Global Wordnet Conference 2021 , Pretoria, South Africa, January 18-21, 2021 online
- 10th Global WordNet Conference 2019 in Wroclaw, Poland, July 23-27, 2019.
- 9th Global WordNet Conference 2018 in Singapore, January 8-12, 2018
- 8th Global WordNet Conference 2016, Bucharest, Romania, January 27-30, 2016
- 7th Global WordNet Conference 2014 in Tartu, Estonia, January 25-29, 2014
- 6th Global WordNet Conference 2012 in Matsue, Japan, January 9-13, 2012
- 5th Global WordNet Conference 2010 in Mumbai, India, January 31 – February 4, 2010
- 4th Global WordNet Conference 2008 in Szeged, Hungary, January 22-25, 2008
- 3rd Global Wordnet Conference 2006 in Jeju Island. Korea, January 22-26, 2006
- 2nd Global Wordnet Conference 2004 in Brno, Czech Republic, January 20-23, 2004
- 1st Global Wordnet Conference 2002 in Mysore, India, January 21-25, 2002