Summary
Shafqat Virk is a researcher in computational linguistics at Språkbanken, University of Gothenburg, with 15 years’ experience building language engineering tools for semantic parsing and information extraction. His PhD work produced resource grammars as reusable software libraries for six Indo-Iranian languages (including Hindi, Urdu, Persian and Punjabi), reflecting a rare blend of linguistic depth and engineering practice. He has led cross-national projects—from Academia Sinica to IRIT—on PropBank and FrameNet–based semantic role labeling and has applied these methods to large-scale, historically grounded corpus work such as Grierson’s Linguistic Survey of India. Based in Gothenburg, he focuses on scalable methods for extracting grammatical and relational information, often combining semantic parsing with open information extraction to make linguistic survey data computationally accessible.
15 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computational Linguistics, Doctor of Philosophy (Ph.D.), Computational Linguistics at Göteborgs universitet / University of Gothenburg
Master of Science (MS), Intelligent Systems Design, 5, Master of Science (MS), Intelligent Systems Design, 5 at Chalmers University of Technology
M.Sc Computer Science, Computer Science, M.Sc Computer Science, Computer Science at Gomal University