C. Anton Rytting

Dr. Anton Rytting is an Associate Research Scientist at the University of Maryland, College Park, Applied Research Laboratory for Intelligence and Security (ARLIS). He has taught for UMD’s College of Information Science (Maryland’s iSchool), Linguistics Department, and the Computer Science Department. Dr. Rytting is a computational linguist with prior work in corpus normalization and quality control, automatic cognate/loanword detection, and natural language processing for under-resourced languages and social media text.

Dr. Rytting led the development of the University of Maryland’s “Did You Mean…?” (DYM) tool, which supports error-tolerant search of lexical resources, and the related DYM toolkit, which allows non-programmers to develop error-tolerant lexical search capabilities for themselves. Dr. Rytting also served as the site Co-Principal Investigator for the UMD contribution to the testing and evaluation (T&E) team for the IARPA Babel program and as the Principal Investigator of a project normalizing speech transcriptions across dialects for colloquial Arabic.  He also served as PI for a project to collect a new corpus and develop language-specific features in social media text predictive of certain personality and cognitive traits.

Dr. Rytting is currently collaborating with Dr. Susannah Paletz (PI) and other University of Maryland researchers on a Minerva Research Initiative grant to study the role of emotional content and narrative in predicting the rate at which social media posts are shared. For more details on this project are available at Emotions in Social Media.

Recent Publications

• Hull, J., Novak, V., Rytting, C.A., Rodrigues, P.R., Frank, V.M., and Swahn M. 2021.  Personality Trait Identification using the Russian Feature Extraction Toolkit.  In Proceedings of the 2021 International Conference on Recent Advances in Natural Language Processing (RANLP 2021).
• Marvi, S., Novak, V., Morrison, M., Gordon, R., Wood, T., Oates, S., Rytting, C.A., Jones, K., Janzen, S., & Maxwell, M. (2021). COVID Needles in Social Media Haystacks: Identifying Cross-Language Longitudinal Changes in Pandemic-Related Discussion Topics. 2021 IdeaS Conference.
• Stepanova, N., Rytting, C.A., Golonka, E., & Paletz, S. (2021). Predicting Popularity of Polish Facebook Posts Using Author and Content Features. Working Paper presented at the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS).
• Rodrigues, P., Novak, V., Rytting, C.A., Yelle, J., Boutz, J., and Buckwalter, T. (2018). Arabic Data Science Toolkit: An API for Arabic Language Feature Extraction.  Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).  Miyazaki, Japan: European Language Resources Association (ELDA).
• Rytting, C. A., & Yelle, J. (2017). DECCA Repurposed: Detecting transcription inconsistencies without an orthographic standard. Proceedings of the 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages, 116–121. https://doi.org/10.18653/v1/W17-0116