Thesis supervisor: Richárd Farkas
Location of studies (in Hungarian): SZTE Abbreviation of location of studies: SZTE
Description of the research topic:
Natural Language Processing (NLP) applications analyse and generate texts. They are business / industrial ready and several companies are now developing their own NLP solutions. The dominant methodology for the development of NLP solutions is supervised machine learning, mostly deep learning systems. These black-box systems only provide an accurate solution if a large amount of labelled training dataset is available, which is usually not the case at the special and ad-hoc tasks of small and medium enterprises. On the other hand, human domain-expert are always available, moreover real business applications require controllability (modifying, extending, etc.) the systems. The goal of the research topic is to develop novel artificial intelligence algorithms, which enables the effective collaboration of human experts and data-driven algorithms in the development and control of NLP systems.
Required language skills: English Number of students who can be accepted: 2