Variation in interpretation is particularly frequent with judgments that depend on an individual’s subjective biases, such as deciding whether a joke is funny or not. This PhD project focuses on NLP methods for subjective interpretive tasks with a high societal relevance, such as offensive/abusive language detection, used e.g., by social media platforms to identify cases of problematic use of language that can be harmful to people. Judgments on whether a given utterance is problematic are notoriously subjective, where differences between judges can have difficult cultural, ethnic, and racial overtones. The project will develop models for detecting problematic language that take into account the fact that the judgments involved can be controversial.

You get the opportunity to partly shape the PhD project based on your own preferences. There are, however, a number of topics we would like to address within the project, also in collaboration with media companies, including:

• What criteria should we follow in creating/choosing data sets to train models for recognising offensive/abusive languages? E.g., how should we collect annotations on potentially controversial text, where judgements can vary widely across annotators? And, is it possible to do this in an automatic fashion, e.g. by leveraging the stance of commentators on social media?
• What kind of deep learning architectures are most appropriate for such tasks? 
• What is the best way for evaluating a model carrying out a type of interpretation when human judgments for that task vary based on factors such as age, gender, and religious belief?

This  position also offers the opportunity to develop teaching skills, next to doing research. Typically, PhD candidates dedicate around 15% of their time to teaching in the department, in the form of tutoring or co-supervision of theses.

You will join the Natural Language Processing (NLP) Group, which is part of the AI & Data Science division of the Department of Information and Computing Sciences. Our current research strengths include the following themes: NLP and Society, Natural Language Generation and, connected with the latter, Vision and Language. In all these areas we work closely with Utrecht University’’s (UU) Language Sciences department. It is foreseen that all PhD projects in the AiNed project will be jointly supervised with Language Sciences. The NLP group contributes to various areas of teaching, for example via UU’s cross-faculty Bachelor and Master’s degrees in Artificial Intelligence. The group is strongly aligned with  UU’s focus area Human-centred Artificial Intelligence.

This PhD position is one of five inter-connected PhD positions focussing on variation in NLP, under Utrecht University’s AiNed project “Dealing with Meaning Variation in NLP”, led by Prof. Massimo Poesio. We are simultaneously recruiting for two other positions in this project. We invite you to also check out these interesting vacancies on our website: PhD position in Natural Language Processing: conflicting interpretations in dialogue and PhD position in Natural Language Processing: variation in co-reference and reference. 

We are looking for a motivated researcher with a curious and critical mindset to join our exciting project. We would also like you to bring:

• a Master’s degree in an area relevant to this project, which lies at the interface between computational social science, NLP, and deep learning. Thus, relevant areas could be Artificial Intelligence, Computational Cognitive Science, Computing Science, Computational Social Science, Linguistics, or Statistics.
• A good mastery of deep learning and of NLP is essential. An understanding of social science methodology would be a definite bonus.
• Excellent English communication skills.
• You take a strong interest in at least two of the three following areas: (1) computational social science, (2) deep learning, and/or (3) NLP.

• A position for 4 years;
• A full-time gross salary that starts at €2,770 and increases to €3,539 per month (scale P of the Collective Labour Agreement Dutch Universities (CAO));
• 8% holiday bonus and 8.3% end-of-year bonus;
• A pension scheme, partially paid parental leave, and flexible employment conditions based on the Collective Labour Agreement Dutch Universities.

In addition to the employment conditions from the CAO for Dutch Universities, Utrecht University has a number of its own arrangements. These include agreements on professional development, leave arrangements, sports and cultural schemes and you get discounts on software and other IT products. We also give you the opportunity to expand your terms of employment through the Employment Conditions Selection Model. This is how we encourage you to grow.

For more information, please visit working at Utrecht University.

A better future for everyone. This ambition motivates our scientists in executing their leading research and inspiring teaching. At Utrecht University, the various disciplines collaborate intensively towards major strategic themes. Our focus is on Dynamics of Youth, Institutions for Open Societies, Life Sciences and Pathways to Sustainability. Shaping science, sharing tomorrow.

At the Faculty of Science, there are 6 departments to make a fundamental connection with: Biology, Chemistry, Information and Computing Sciences, Mathematics, Pharmaceutical Sciences, and Physics. Each of these is made up of distinct institutes that work together to focus on answering some of humanity’s most pressing problems. More fundamental still are the individual research groups – the building blocks of our ambitious scientific projects. Find out more about us on YouTube.

The Department of Information and Computing Sciences is nationally and internationally known for its research in computer science and information science. The Department provides and contributes to the undergraduate programmes in Computer Science, Information Science, and Artificial Intelligence and a number of research Master's programmes in these fields. It employs over 200 people, working in four divisions: Interaction, Algorithms, Data Science & Artificial Intelligence and Software. The atmosphere is collegial and informal.