PhD Fellow in Explainable Natural Language Understanding, Natural Language Processing Section, Department of Computer Science, Faculty of Science, University of Copenhagen
The Natural Language Processing Section at the Department of Computer Science, Faculty of Science at the University of Copenhagen is offering a PhD scholarship in Explainable Natural Language Understanding commencing on 1 September 2024.
Description of the scientific environment
The Natural Language Processing Section provides a strong, international and diverse environment for research within core as well as emerging topics in natural language processing, natural language understanding, computational linguistics and multi-modal language processing. It is housed within the main Science Campus, which is centrally located in Copenhagen. Further information about research at the Department is available here: https: // di.ku.dk/english/research/. The successful candidate will join Isabelle Augenstein's Natural Language Understanding research group (www. copenlu.com/). The Natural Language Processing research environment at the University of Copenhagen is internationally leading, as e.g. evidenced by it being ranked 2nd in Europe according to CSRankings.
Project description The PhD fellowship is offered in the context of an ERC Starting Grant held by Isabelle Augenstein on ‘Explainable and Robust Automatic Fact Checking (ExplainYourself)'. ERC Starting Grant is a highly competitive funding program by the European Research Council to support the most talented early- career scientists in Europe with funding for a period of 5 years for blue- skies research to build up or expand their research groups.
ExplainYourself proposes to study explainable automatic fact checking, the task of automatically predicting the veracity of textual claims using machine learning (ML) methods, while also producing explanations about how the model arrived at the prediction. Automatic fact checking methods often use opaque deep neural network models, whose inner workings cannot easily be explained. Especially for complex tasks such as automatic fact checking, this hinders greater adoption, as it is unclear to users when the models' predictions can be trusted. Existing explainable ML methods partly overcome this by reducing the task of explanation generation to highlighting the right rationale. While a good first step, this does not fully explain how a ML model arrived at a prediction. For knowledge intensive natural language understanding (NLU) tasks such as fact checking, a ML model needs to learn complex relationships between the claim, multiple evidence documents, and commonsense knowledge in addition to retrieving the right evidence. There is currently no explainability method that aims to illuminate this highly complex process. In addition, existing approaches are unable to produce diverse explanations, geared towards users with different information needs. ExplainYourself radically departs from existing work in proposing methods for explainable fact checking that more accurately reflect how fact checking models make decisions, and are useful to diverse groups of end users. It is expected that these innovations will apply to explanation generation for other knowledge-intensive NLU tasks, such as question answering or entity linking.
The project team will consist of the principle investigator, three PhD students and two postdocs, collaborators from CopeNLU as well as external collaborators. The role of the PhD student to be recruited in this call will be to research methods for generating faithful free-text explanations of NLU models in collaboration with the larger project team.
The principal supervisor is Professor Isabelle Augenstein , Department of Computer Science, e-mail: [email protected]. The PhD student will be co-supervised by Postdoctoral Researcher Pepa Atanasova, Department of Computer Science, email: [email protected].
The position is available for a 3-year period. The key tasks as a PhD student at SCIENCE are:
Formal requirements Applicants should hold a MSc degree or equivalent in Computer Science or a related field, and have good written and oral English skills. The assessment of your qualifications will also be made based on previous scientific publications (if any) and relevant work experience. The ideal candidate would have an education background, prior research or work experience in ML or NLP.
Terms of employment
The position is covered by the Memorandum on Job Structure for Academic Staff.
Terms of appointment and payment accord to the agreement between the Ministry of Finance and The Danish Confederation of Professional Associations on Academics in the State.
The application, in English , must be submitted electronically by clicking APPLY NOW below.
The University wishes our staff to reflect the diversity of society and thus welcomes applications from all qualified candidates regardless of personal background.
The deadline for applications is 1 February 2024 , 23:59 GMT +1.
After the expiry of the deadline for applications, the authorised recruitment manager selects applicants for assessment on the advice of the Interview Committee. Afterwards, an assessment committee will be appointed to evaluate the selected applications. The applicants will be notified of the composition of the committee and the final selection of a successful candidate will be made by the Head of Department, based on the recommendations of the assessment committee and the interview committee.
The main criterion for selection will be the research potential of the applicant and the above-mentioned skills. The successful candidate will then be requested to formally apply for enrolment as a PhD student at the PhD school of Science. You can read more about the recruitment process at https: // employment.ku.dk/faculty/recruitment-process/ .
For specific information about the PhD scholarship, please contact the principal supervisor, Professor Isabelle Augenstein, Department of Computer Science, [email protected].
General information about PhD programmes at SCIENCE is available at https: // www. science.ku.dk/phd.