PhD Position in Machine Learning Models for the Verification of Information and Detection of Disinformation KU Leuven Informatics Section Belgium



KU Leuven and the Joint Research Centre (JRC) of the European Commission are inviting applications for PhD positions through the Collaborative Doctoral Partnership (CDP) scheme. The CDP scheme intends to enhance the science-policy link through strategic collaborations with higher education institutions characterized by research excellence and international reputation, in order to: * Train a new generation of doctoral graduates in science and technology with a focus on the science-policy interface, able to understand the research needs at different stages of the policy cycle, capable of providing scientific support to policy and of using transferable skills in science communication and knowledge management. * Co-develop, co-host and co-supervise doctoral studies between higher education institutions and the JRC. * Strengthen collaboration between the JRC and higher education institutions by promoting mutual enhancement of related skills and competences, combining existing knowledge and capacities, and enhancing networking in key scientific areas.



Within the CDP scheme we offer a PhD position in Machine learning models for the verification of information and detection of disinformation. Verification of information becomes a primordial task in any information management setting. In this PhD research we primarily focus on the verification of textual information but do not exclude the use of additional sources of information such as accompanying images and linked content (in case of Web documents).
A first goal of the PhD is to extract facts or claims from text and their supporting and non-supporting arguments that are mentioned in the text or in other sources. An intuitive approach is to use deep neural networks that are also trained to detect negation and modality in text. An additional focus will be on training extraction models with limited annotated examples and on investigating the transfer of models trained in one domain to another domain. In order to detect disinformation, the resulting content representations will be compared with those of facts and arguments extracted from other texts and possibly extracted from other sources or with those that are available in knowledge repositories. This second goal also entails learning how to fuse information and studying what types of representations are best suited in this process, in which supporting evidence as well as contradictory evidence will be detected. Again, this can be done in a deep learning setting, where a large focus will be on the explanation of the network that predicts the probability of disinformation. Investigation of the weights of the trained network will contribute to the explanations, but in a final challenging goal the PhD will investigate whether from the obtained content representations we can automatically generate natural language explanations of the decisions taken by the system with regard to disinformation. This language generation task can be trained in a multitask setting, jointly with the prediction of disinformation. 
The research will be evaluated using benchmarking datasets obtained from traditional and social media platforms. The novel methods developed during the PhD research will be compared with strong state-of-the-art baselines for information extraction from text, transfer learning, information fusion and text generation described in the scientific literature.


  • You have (or are near completion of) a Master in Computer Science (or a related field). 
  • You have a motivated interest in research in natural language processing and machine learning. 
  • You work proactively and independently and have good communication skills.
  • You have a very good knowledge of English, both spoken and written.
  • You are highly motivated, ambitious and result-oriented.


  • We offer a four-year PhD position in collaboration with the Joint Research Centre (JRC) of the European Commission.
  • The PhD research will be realized at the Department of Computer Science of the KU Leuven and at the Joint Research Centre (JRC) in Ispra, Italy (at JRC for a period of up to 24 months).
  • We offer a competitive fellowship. While at the JRC in Ispra, you will get a contract as a grant holder Category 20 (see 



For more information please contact Prof. dr. Marie-Francine Moens, tel.: +32 16 32 53 83, mail: or Prof. dr. ir. Hendrik Blockeel, tel.: +32 16 32 76 43, mail: of the Department of Computer Science of the KU Leuven.

The selection process is based on the CV, tests and interviews. It is composed of two phases, that is, a first selection is made by KU Leuven resulting in a short list of candidates and then a second selection is made by JRC. Candidates should at the start of the employment contract with JRC:
* Have the nationality of a Member State of the EU or a country associated to the Research Framework Programmes (Horizon2020). 
* Be enrolled in a PhD programme at KU Leuven. 

You can apply for this job no later than February 28, 2019 via the online application tool

KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at

If you apply for this position please say you saw it on Computeroxy


All Jobs


Harvard University Academic Positions

Kuwait University Current Faculty Openings

Osaka University Academic Opportunities

Purdue University Job Postings for Faculty Positions

Texas Tech University Faculty Openings

Tsinghua University Job Postings

University of Cambridge Job Openings

University of Geneva Faculty Opportunities

University of New South Wales Job Openings

University of Nottingham Research Positions

University of Oslo Academic Jobs

University of Saskatchewan Faculty Positions

University of Southampton Research Vacancies

University of Tokyo Current Academic Vacancies

University of Toronto Open Faculty Positions