Aleksandr Perevalov

Fachbereich 5 - Informatik und Sprachen

Aleksandr Perevalov

PhD student and research staff at the chair “Web Engineering” of the department “Computer Science and Languages”.
Field of research: Question Answering over Knowledge Graphs, Multilingual Aspect of Accessibility of Web Systems, Quantitative Text Analysis

Achievements

• 2018 - 1st prize in the Perm University conference with research about the improvement of speech recognition quality of the “CMU Sphinx” system. Perm, Russia.
• 2018 - TOP10 in Machine Learning competition within the Russian Artificial Intelligence forum (production time prediction). Moscow, Russia.
• 2019 - TOP9 in international data analysis competition Data Mining Cup 2019 (self-checkout fraud detection). Berlin, Germany.
• 2020 - Bronze medal on Kaggle.com ”Jigsaw Multilingual Toxic Comment Classification” competition.

Lebenslauf

• 09.2014 - 08.2018: Perm National Research Polytechnic University
  Perm, Russia
  Bachelor in “Informatics and Computing Technology”
• 03.2018 - 08.2020: Foresight LLC
  Perm, Russia
  Software developer (BPM-System)
• 09.2018 - 08.2020: Perm National Research Polytechnic University
  Perm, Russia
  Master in “Informatics and Computing Technology”
  Diploma with distinction
• 10.2019 - 08.2020: Hochschule Anhalt
  Köthen (Anhalt), Germany
  Master in “Data Science” (Double degree)
• since 08.2020: Hochschule Anhalt
  Köthen (Anhalt), Germany
  Research staff

Publikationen

• Enhancing Multilingual Accessibility of Question Answering over Knowledge Graphs / Perevalov, Aleksandr. - Enthalten in: Laforest, Frédérique. Proceedings of the ACM Web Conference 2022 (2022), S.349-353
• QALD-9-plus : a mulitlingual dataset for question answering over DBpedia and Wikidata translated by native speakers / Perevalov, Aleksandr. - Enthalten in: De.arxiv.org (2022)
• Improving Question Answering Quality Through Language Feature-Based SPARQL Query Candidate Validation / Perevalov, Aleksandr. - Enthalten in: Groth, Paul. The Semantic Web (2022), S.217-235
• show all publications in OPAC