PhD Candidate for Data Augmentation for Conversational AI (project 1)

Are you an aspiring researcher and would you like to work on algorithmic solutions to solve challenges in conversational intelligence? Start your academic career off right as a PhD candidate within the NWO-funded LESSEN project. Join a diverse team of researchers based at multiple Dutch universities and work with several industrial stakeholders to develop chat-based conversational agents.

The institute for Computing and Information Sciences (iCIS) at Radboud University is looking for a PhD candidate to work on the project "LESSEN: Low Resource Chat-based Conversational Intelligence" . The project aims to develop, implement and evaluate state-of-the-art safe and transparent chat-based conversational AI agents based on state-of-the-art neural architectures. The focus is on lesser resourced tasks, domains and scenarios. The project is funded by an NWO Dutch Research Agenda grant awarded to a consortium consisting of the University of Amsterdam, Leiden University, the University of Groningen, Amsterdam University of Applied Sciences, Radboud University, Achmea, Albert Heijn, Bol.com, KPN, Rasa Technologies, Ahold Delhaize, and the Dutch national police force. You will work on the project under the supervision of a team consisting of Dr Faegheh Hasibi (Radboud University), Prof. Maarten de Rijke (University of Amsterdam) and Prof. Arjen P. de Vries (Radboud University).

The aim of this PhD project is to make efficient use of existing knowledge for developing conversational agents under data scarcity conditions. Conversational agents require large amount of training data to handle complex user requests about objects or abstract concepts. Structured information that is stored in knowledge graphs can be used to enrich data-hungry conversational models. In this project, you will inject information from knowledge graphs into transformer-based models and generate knowledge-enriched conversational agents, without requiring large amount of unstructured training data. You will pursue your PhD in a vibrant international research environment in the data science group of iCIS at Radboud University, with top-notch professors and researchers in information retrieval and machine learning. iCIS values a diverse workforce. Female candidates are therefore particularly encouraged to apply. Your teaching load may be up to 10% of your appointment.