Research
Work at the intersection of linguistics and NLP
Publications
Conference Paper
A Semi-Automated Approach to the Annotation of Argument Structures in Turkish Datasets
GWC2025 (Global WordNet Conference), Pavia, Italy · 2025
Research on automating argument structure annotation in Turkish using Abstract Meaning Representation frameworks.
AMRTurkish NLPUniversal DependenciesFrameNet
Research Projects
TÜBİTAK ProjectCompleted
Turkish AMR & Question Answering System
2023 – 2025 · 36 months
A multi-layer NLP project building a comprehensive Turkish FrameNet, integrating it with the existing Turkish PropBank (TRopBank) and dependency treebanks to produce semi-automatic Abstract Meaning Representations (AMR) for Turkish, with a graph neural network-based question answering system as the downstream application.
Research Interests
Natural Language ProcessingAbstract Meaning RepresentationTurkish LinguisticsUniversal DependenciesComputational LinguisticsLanguage GroundingQuestion AnsweringGraph Neural NetworksSemantic Role Labeling
Ventures & community projects →