PhD student. Jue works on scalability of the back end and the front end, and educational data science — to analyze and model data collected from proof-of-concept studies with real learners. His research focuses on modeling learner proficiency and novel approaches to language modeling deep-learning neural nets.
Jue Hou's People finder profile
Jue Hou's Research portal profile
PhD Student. Anisia works on all aspects of user studies involving Russian. Her research is on building deep-learning language models for detection of grammatical errors. Revita needs such models to identify "alternative-correct" answers — important situations in learning, where more than one answer is possible for an exercise.
Anisia Katinskaia's People finder profile
Anisia Katinskaia's Research Portal profile
MS student. Ilmari works with the TOSKA Group, under the direction of Dr Matti Luukkainen, to bring the latest developments in front-end technologies into Revita — to assure the best possible User Experience for the learners and teachers. He is working on his MS degree in Language Technology.
Ilmari Kylliäinen's People finder profile
Ilmari Kylliäinen's Research portal profile
PhD Student. Duc works on Bayesian networks and deep learning modeling of the learners' proficiency and progress, which is essential for personalization in the Revita Project — learner competency must be modeled accurately to provide the most suitable exercises and feedback.
Duc's MS Thesis (2020) was on "Modeling knowledge states in language learning."
Project lead. Roman Yangarber is Associate Professor at the Department of Digital Humanities, University of Helsinki (UH). He holds the Chair in Linguistic Inequalities and Translation Technologies at INEQ: The Helsinki Inequality Initiative. His research group — the Language Learning Lab — works on a variety of topics: studying how language works, and how computers can better understand language. His earlier research themes include analysis of news media, and modeling language evolution. More recent focus is on AI support for language learning. This has resulted in a system currently in use by learners and teachers at several universities. The research focuses on support for learning of smaller, endangered languages, as well as for "majority" languages.
Roman Yangarber's People finder profile
Publications (Google Scholar)
Here are some of our main contributors: local, at the University of Helsinki (UH), and international.
Remote Studies — are current work with groups of learners at other universities, collecting feedback from them and researching their progress.
- Annel Baktybaeva — Lecturer (Asfendiyarov Kazakh National Medical University, Almaty, Kazakhstan). Remote studies with university-level learners of Russian and Kazakh.
- Elena China-Kohlemainen — Master's student (UH). Support for Italian, creating the inventory of linguistic concepts, and the hierarchy of feedback for learner mistakes.
- Lari Kotilainen — University lecturer (UH). Principal advisor for Finnish linguistics and didactics.
- Mihail Kopotev — Professor (Higher School of Economics, St Petersburg, Russia), University lecturer (UH). Principal advisor for Russian linguistics and didactics.
- Matti Luukkainen — University lecturer (UH). Leads the TOSKA reseach group on Software Engineering and Web development. Primary advisor on best practices and the latest techniques for Software Engineering in Revita. Supervising Gert Adamson, Atte Haarni, Esa Kemppainen, Jami Kousa, Ilmari Kylliäinen, Tero Tapio, and other TOSKAns making substantial contributions to Revita's development.
- Mihail Mikhailov — Professor (Translation Studies, Tampere University, Finland). Remote studies with university-level learners of Finnish and Russian.
- Dr Nataliya Stoyanova — Researcher (State University of Milan, Italy). Principal advisor for Russian linguistics and didactics. Remote studies with university-level learners of Russian.
- Graphic Design Team: Vesna Hendry, Tommaso Furlan — (Udine, Italy). Design of user interface and user experience.
- Mikhail Zolotilin — MA student (UH). Resources for syntactic government (Russian).
All of our colleagues and collaborators typically work on multiple problems and aspects of the Project at the same time, and contribute to many areas. We list here some of them here:
- Javad Nouri — MS Student. Javad built all components of the first functioning Revita platform. Initial focus on several endangered Finno-Ugric languages, Finnish, Russian.
- Kim Salmi — MS Student. Contributed to many front-end and back-end aspects of the early platform.
- José María (Txema) Hoya Quecedo — MS Student. The core back-bone for supporting cross-language handling of morphological analysis and for (shallow) syntactic analysis. NLP topics: models of ambiguity and disambiguation. Initial support for Romance languages (β).
- Max Koppatz — MS Student. Major improvements to the language-analysis layer and to exercise selection. NLP work: deep-learning language modeling. Language specific work on Finnish, initial support for Swedish and German (β).
- Tomi Rikander — MS Student. Front-end improvements and re-ingeneering.
- Sardana Ivanova — PhD Student. Support for Russian, Sakha (Yakut).
- Gert Adamson — MS Student. New front-end, enhanced user experience.