Researcher in Natural Language Processing/Data science
University of Gothenburg
The University of Gothenburg tackles society’s challenges with diverse knowledge. 53 500 students and 6 500 employees make the university a large and inspiring place to work and study. Strong research and attractive study programmes attract scientists and students from around the world. With new knowledge and new perspectives, the University contributes to a better future.
The position focus: identification of lexical semantic change using computational models applied to diachronic texts
Språkbanken (SB) is a nationally and internationally acknowledged with unit at the Department of Swedish, University of Gothenburg, established in 1975. Our work focuses on Language Technology (LT), Natural Language Processing (NLP), and computational linguistics (CL), primarily for the Swedish language, and the development of linguistic resources and tools Swedish. SB is the coordinating partner of the research project “Towards computational lexical semantic change detection” (a project funded by a grant from the Swedish Research Council). The successful applicant will conduct research in this project, more information regarding the project can be found on www.languagechange.org. The research will be conducted in collaboration with researchers from Chalmers University of Technology and Stockholm University.
The successful applicant will conduct research in NLP/data science in order to develop and implement methods for processing, detecting, and evaluating lexical semantic change using diachronic texts. In particular, you will be using machine learning, deep learning, and topic modeling, to automatically detect semantic change using large collections of historical texts. You will evaluate your results on English and Swedish document collections, on evaluation sets like SemEval-tasks for word sense induction, unsupervised semantic change detection, and other existing change testsets. You will also use the developed models to investigate qualitative hypotheses posted by researchers from history, linguistics, and social sciences. We collaborate by regular meetings in which you will take an active part in the discussions and present results. Your work contributes to scientific progress which is presented in jointly published journal papers, as well as national and international conferences.
We are seeking a candidate who on a personal level is independent and self-motivated. The candidate should have experience with lexical semantic change detection, and/or evaluation, with historical large-scale data (including processing of dirty texts with OCR errors), and data science investigations into large-scale data. Previous experience with historical linguistics is a plus. Proof of research and scientific writing skills must be provided with the application (i.e. in the form of CV and relevant publications). At minimum, the candidate must possess a PhD degree in a relevant field, like historical linguistics with a focus on computational modeling, information science, language technology, or computer science with a strong focus on NLP. A documented record of work performed in the field of lexical semantic change detection, and/or evaluation, is required. The degree should generally not to be older than 6 years at the time of application.
The assessment of your application will be based mainly on your scientific skills. You are expected to provide evidence of excellence in research. In the assessment of scientific proficiency, special attention will be paid to your relevant NLP/data science work with lexical semantic change detection and/or evaluation. The main considerations in ranking candidates will be quality of their scientific track record and how central previous research is to the research questions outlined by the project. Excellent skills regarding scientific communication in English, the high degree of independence, and critical thinking are also expected. In addition, a high weight will be given to previous experience with deep learning methods, such as skip-gram with negative sampling, and BERT, as well as topic modeling, all applied to historical data.
The work requires that you are highly independent. Large weight will be given to personal skills such as:
- Being flexible and adaptable to changing circumstances.
- Being responsible, working in a structured way, and following time plans.
- Taking initiative, and getting started and producing results.
- Being good at communicating research and results such that other people understand, both laymen and researchers from other fields.
The employment is a fixed term employment of 40 %, with placement at the Department of Swedish. First day of employment: 2022-01-08 and last day of employment: 2022-05-19
For further information regarding the position
If you have questions regarding the position, please contact: Nina Tahmasebi, researcher.
Union representatives at the University of Gothenburg:
Information for International Applicants
Choosing a career in a foreign country is a big step. Thus, to give you a general idea of what we and Gothenburg have to offer in terms of benefits and life in general for you and your family/spouse/partner please visit:
How to apply
In order to apply for a position at the University of Gothenburg, you have to register an account in our online recruitment system. It is the responsibility of the applicant to ensure that the application is complete in accordance with the instructions in the job advertisement, and that it is submitted before the deadline. The selection of candidates is made on the basis of the qualifications registered in the application.
Closing date: 2021-10-14
The University of Gothenburg promotes equal opportunities, equality and diversity.
Salary is determined on an individual basis.
Applications will be destroyed or returned (upon request) two years after the decision of employment has become final. Applications from the employed and from those who appeal the decision will not be returned.
In connection to this recruitment, we have already decided which recruitment channels we should use. We therefore decline further contact with vendors, recruitment and staffing companies.