• prof. dr. Els Stronks

• Sarah Bro Trasmundi — University of Southern Denmark

With Henk Aarts and Hans Marien (both Social and Behavioural Sciences), and Mehdi Dastani and Marijn Schraagen (Information and Computing Sciences); the aim of this project is to design and develop AI tools for detecting and preventing low literacy in Dutch children, and for providing adequate and personalized support for improving literacy (with the Foundation for Open Speech Technology, Fontys University of Applied Sciences, Royal Library, Stichting Lezen, and other potential partners.

• prof. dr. M.M. (Mehdi) Dastani
• dr. Hans Marien
• prof. dr. Henk Aarts
• prof. dr. Els Stronks

Within the dynamic linguistic situation of the Dutch Golden Age, we observe a type of language variation that has rarely been addressed before: variation within individual language users (intra-author variation). This becomes especially clear in the way 17th century authors use negation: they express negation in the Middle Dutch way (i.e. embracing negation, a combination of the negative clitic en and a negative particle niet; compare French ne…pas) as well as in the modern way (single negation: niet). In this Nederlab pilot project, we aim to describe and analyze in detail the linguistic and literary/rhetorical contexts in which these two variants of negation occur within the letters of the famous Dutch author and politician P.C. Hooft, written between 1600 and 1638. In this period, he used both forms of negation: as earlier research has demonstrated, Hooft stopped using embracing negation in 1638. This pilot project will enrich Hooft’s letters in the Nederlab corpus in such a way that we are able to search for grammatical properties that are specific for 17th century Dutch. We will then analyze in which linguistic, literary and sociolinguistic contexts specific types of negation and negation particles were used.

• prof. dr. Marjo van Koppen

The vibrant political, religious and cultural atmosphere of the Dutch Golden Age interacted with language. 17^th century Dutch was a mixture of fading linguistic properties from the preceding language phase, Middle Dutch, and upcoming new ways to construct words and sentences. These language innovations were partly driven by migration, literary innovations and standardization processes.

Within these language dynamics we observe a type of language variation that has rarely been addressed before: variation within individual language users (intra-author variation). The famous author P.C. Hooft, for instance, uses the Middle Dutch way to express negation as well as a modern alternative. How can we account for this variation, seemingly randomly displayed by authors? This project will chart and explain the grammatical properties of intra-author variation, as well as the social- and literary-cultural factors that influenced the way individual authors used their variation in a strategic and/or creative way. The central hypothesis of the project is that the (internal) grammars of authors created a particular range of variation, which was systematically used by authors, based on contextual factors.

We develop a new line of interdisciplinary research as a necessary condition for an in-depth understanding of language variation, combining approaches from theoretical linguistics, historical sociolinguistics, computational linguistics and literary studies. We qualitatively investigate 1) how variation follows from the (internal) grammar, and 2) is related to the social and literary context, and we quantitatively investigate 3) variation patterns within and between authors and genres.

• prof. dr. Marjo van Koppen
• dr. Joanna Wall

In the project "Intelligente Reporting" we aim to, together with the Dutch Police, provide an Artificial Intelligence framework for automatically processing online reports on cybercrime submitted by the public.

The framework uses a peer-to-peer approach: every part of the reporting process is handled by an individual module, which facilitates incremental implementation and connections to legacy systems. Data is only accessible by people interfacing with a specific module, and only the necessary information is shared between modules, which guarantees privacy.

We use a hybrid of machine learning techniques for recognising patterns in data and more transperant and understandable knowledge-based (argumentation) models. This allows us to use recent insights in AI in a responsible and explainable way. 

• prof. dr. Floris Bex

• Daphne Odekerken