The LATTICE Lab centers its research on two core themes: conversational intelligence and low resource chat-based conversational intelligence.
To drive these advancements, the lab leverages key technical AI components, focusing primarily on:
With a commitment to socially aware, explainable, and responsible systems.
The LATTICE Lab is dedicated to advancing research in the field of conversational AI.
The lab’s mission and vision are to democratize human language technology and conversational AI, specifically for the Dutch language, by reducing reliance on major international tech companies.
The impact of the lab lies in building several technical AI foundations -natural language processing, machine learning, and information retrieval – while emphasizing multidisciplinary aspects like explainable, socially aware, and responsible AI.
WP1.1: Neural Architectures – Focuses on designing neural architectures for chat agents that are efficient in terms of training, memory, and inference.
WP1.2: Efficient Data Use – Develops ways to use existing data from different languages and forms, such as entity graphs, to empower AI even when data is scarce.
WP2.1: Domain-Specific Challenges – Aims to solve the hurdles of developing conversational agents in specific fields by transferring knowledge from other, data-rich domains.
WP2.2: Synthetic Data Generation – Focuses on creating methods to generate artificial data for training the data-hungry models needed for conversational agents.
WP3.1: Safety, Security, and Privacy – Dedicated to detecting and preventing unsafe interactions in dialogues while investigating critical privacy and security issues.
WP3.2: Agent Transparency – Works on algorithms that can generate model explanations for stakeholders to ensure the AI’s operations are transparent.
WP4: Robust Evaluation – Focused on developing rigorous evaluation methods and tools specifically for Large Language Models (LLMs) and conversational agents.
WP5: Knowledge Integration and Dissemination – Aimed at integrating and sharing the knowledge and research outputs generated across the lab with both consortium members and external parties.
Leiden University is a leading research university in the Netherlands that serves as the main contact institute for the lab, focusing on AI foundations like Natural Language Processing and Machine Learning.
University of Amsterdam is a major academic institution providing expertise from several professors in AI research and serving as a key site for the lab’s PhD researchers.
University of Groningen is the research university contributing expert faculty to lead and supervise research lines within the conversational AI project.
Radboud University Nijmegen the knowledge institution providing specialized research input and supervision for the lab’s work packages.
Amsterdam University of Applied Sciences (HvA) focuses on applied research and hosts workshops to bridge the gap between companies and PhD students.
Achmea is one of the largest insurance and financial service providers in the Netherlands.
Ahold Delhaize – major international food retail group that operates supermarkets and e-commerce platforms.
Albert Heijn – leading supermarket chain in the Netherlands, focused on retail and customer service innovation.
Bol.com – prominent Dutch e-commerce site and online marketplace that provides data for the lab’s research projects.
KPN – primary Dutch telecommunications and IT service provider, which collaborates closely with the lab’s PhD researchers.
Rasa Technologies – technology company that provides open-source infrastructure for building conversational AI and chatbots.
Politie – Dutch national police force, which serves as a cooperation partner to apply research in a public safety and societal context.
