Исследователь, разработчик, сооснователь компании Meanotek AI
Примечательные научные публикации в области искусственного интеллекта:
Tarasov, D. S., Matveeva T, Galliulina N. An Empirical Investigation Of Language Model Based Reverse Turing Test As A Tool For Knowledge And Skills Assessment. Computational Linguistics and Intellectual Technologies:Proceedings of the International Conference “Dialogue 2020”
Tarasov, D. S., Matveeva T, Galliulina N. Language Models For Unsupervised Acquisition Of Medical Knowledge From Natural Language Texts: Application For Diagnosis Prediction. Computational Linguistics and Intellectual Technologies:Proceedings of the International Conference “Dialogue 2019”
Tarasov D. S., Izotova E. D. Common sense knowledge in large scale neural conversational models //International Conference on Neuroinformatics. – Springer, Cham, 2017. – С. 39-44.
Tarasov D.S. (2016) Neural network model for general domain question answering//Proceedings of International Conference on Artificial Neural Networks — Neuroinformatics (2016) V.3. In this work we propose novel neural network model, capable of answering questions without topic restriction by reading natural language documents provided by simple information retrieval methods. (paper in Russian, for English abstract see conf. program neuroinfo.ru/index.php/en/schedule/sections?year=2016 paper text available by request))
Tarasov D.S. (2015) Natural Language Generation, Paraphrasing and Summarization of User Reviews with Recurrent Neural Networks // Computational Linguistics and Intellectual Technologies: Proceedings of Annual International Conference “Dialogue”, Issue 14(21), V.1, pp. 571-579 (PDF link: www.dialog-21.ru/digests/dialog2015/materials/pdf/TarasovDS2.pdf, presentation slides: www.meanotek.io/files/natgen.pdf). This paper, reports the first successful application of deep learning to generate abstractive multi-document summaries.
Tarasov D.S. (2015) Deep Recurrent Neural Networks for Multiple Language Aspect-Based Sentiment Analysis // Computational Linguistics and Intellectual Technologies: Proceedings of Annual International Conference “Dialogue”, Issue 14(21), V.2, pp. 65-74 (PDF link: www.meanotek.io/files/TarasovDS2015-Dialogue.pdf) — this paper describes aspect-based sentiment analysis system that achieved top results on SentiRuEval-2015 competition (http://www.dialog-21.ru/evaluation/2015/sentiment/)
Другие интересные публикации:
Tarasov, D., Akberova, N., Izotova, E., Alisheva, D., Astafiev, M., & Freitas Jr, R. A. (2010). Optimal tooltip trajectories in a hydrogen abstraction tool recharge reaction sequence for positionally controlled diamond mechanosynthesis. Journal of Computational and Theoretical Nanoscience, 7(2), 325-353.
Tarasov, D., Izotova, E., Alisheva, D., Akberova, N., & Freitas Jr, R. A. (2011). Structural stability of clean, passivated, and partially dehydrogenated cuboid and octahedral nanodiamonds up to 2 nanometers in size. Journal of Computational and Theoretical Nanoscience, 8(2), 147-167.
