The CLiPS research group on Computational Linguistics of the department of Linguistics (Faculty of Arts) has a full-time vacancy for a senior (postdoc) Researcher in the area of Computational Linguistics (Natural Language Processing) for an FWO (Flemish NSF) funded project on “The Linguistic Landscape of Hate Speech in Social Media.”
The CLiPS computational linguistics group is part of the CLiPS research center (http://www.uantwerpen.be/clips) associated with the linguistics department at the University of Antwerp. It has a long tradition and strong international reputation in natural language understanding, text analytics, machine learning, computational psycholinguistics, and digital humanities. Together with the CLiPS research groups on child language acquisition, psycholinguistics, and sociolinguistics, we provide a strong interdisciplinary environment combining methodologies and insights from linguistics, psycholinguistics, computer science, artificial intelligence, corpus linguistics, and cognitive science. The group has available a state of the art computing and experimentation infrastructure and a broad range of national and international collaborations with both academic and industrial partners.
Hate speech online is a widespread social phenomenon. We are interested in the language that is being used to express hate in social media, specifically hate against migrants and LGBT people, and in automatically detecting it. In this project, in cooperation with the Department of Translation (University of Ljubljana, Slovenia) and the Department of Knowledge Technologies (Jozef Stefan Institute, Slovenia), we will collect data, and will develop methods to automatically analyze the language in these texts. The analysis will be on different linguistic levels and different levels of complexity. At CLiPS we will focus on English and Dutch. Apart from the linguistic description of the phenomena, the main goal of CLiPS in this project is to build systems that can automatically recognize and analyse hate speech in social media text.
The postdoc researcher
• will be responsible for developing and evaluating new algorithms for linguistic analysis and automatic detection of hate speech and implementing them in Python modules;
• will assist the project coordinator with the management of this and related projects at CLiPS;
• will coordinate the CLiPS research with that of the project partners in Slovenia;
• will co-supervise PhD researchers employed on this and related projects;
• will publish and present research results in international peer reviewed journals and conferences;
• will be involved in competitive efforts to acquire additional funding. Profile and requirements
• You hold (or will obtain during the application period) a doctorate (PhD) in Computer Science, Engineering, Computational Linguistics or other relevant areas.
• You have expertise in Computational Linguistics (Natural Language Processing), and Machine Learning.
• You have excellent programming skills (at least in Python and preferably in statistical packages like R or Matlab).
• You have an excellent track record of publications in high-impact journals.
• You have excellent English language skills in academic writing and presentation.
• You are a team player, comfortable with working in a complex project involving multidisciplinary colleagues in different research groups.
• Knowledge of Dutch (for understanding part of the data) is an advantage. We offer
• We offer a full-time position for one year, extendible to four years, in a vibrant research environment with state-of-the-art infrastructure, and cooperation with strong research groups and industrial partners.
• Your full time gross monthly salary will range between € 4.134,93 and € 6.446,00 depending on previous experience.
• The earliest start of the project is February 1, 2019. Application Instructions
Please send an extended CV and motivation letter to Walter Daelemans (walter.daelemans at uantwerpen.be), before the closing date of January 11, 2019. Questions about the profile and the description of work can be sent to that address as well. \