Greg Kondrak - Alberta Machine Intelligence Institute

Grzegorz (Greg) Kondrak

Fellow

Academic Affiliations

Professor – University of Alberta (Computing Science); Principal Investigator – xAI Lab (University of Alberta)

Areas of Expertise

Artificial intelligence; computational linguistics; natural language processing; computational morphology and phonology; transliteration; grapheme-to-phoneme conversion; cognate identification

Greg Kondrak works in the area of natural language processing (NLP) and, more broadly, in computational linguistics.

Learning and Linguistics

Grzegorz (Greg) Kondrak works in the area of natural language processing (NLP) and, more broadly, in computational linguistics. His work in character-level processing includes letter-to-phoneme conversion, transliteration, syllabification and stress prediction. He also works to create systems that can identify cognates (words that are similar across different languages), and seeks to apply cognates in various areas of NLP for activities such as language reconstruction, sentence and word alignment in bitexts, machine translation and detecting confusable drug names. Through his research, he also develops methods for computing orthographic, phonetic and semantic word similarities and works to apply NLP for bioinformatics. His work can be applied to language reconstruction, machine translation and detecting confusable names. Greg is well known for his work on deciphering the Voynich manuscript and for proving wrong Noam Chomsky’s famous statement that English orthography is “close to optimal.”

Greg is a Fellow at Amii and a Professor of Computing Science at the University of Alberta. He has co-authored more than 100 publications at venues such as the Artificial Intelligence Journal, the conferences of the Association for Computational Linguistics (ACL), and the International Joint Conference on Artificial Intelligence – where he won a Best Paper Award in 1995. He has been the Program Chair for the International Conference on Natural Language Processing as well as for workshops at the ACL conference. He has also served as the area or local chair for the Annual Conference of the North American Chapter of the ACL and for the Canadian AI Conference. Greg has supervised more than 15 students, many of whom have received Undergraduate Student Research Awards from the National Sciences and Engineering Research Council. His research has been featured by CBC News and by the scientific journal Nature.