Project Details

Rozsáhlá extrakce informací a využití herních principů (gamifikace) pro osvojování nových jazyků na základě "moudrosti davů" (crowdsourcingu)

Project Period: 1. 6. 2018 – 28. 2. 2021

Project Type: grant

Code: LTC18006

Agency: Ministerstvo školství, mládeže a tělovýchovy ČR

Program: INTER-EXCELLENCE - Podprogram INTER-COST

English title

Large-Scale Information Extraction and Gamification for Crowdsourced Language Learning

Type

grant

Keywords

Gamification; Language learning; Extraction of information; Crowdsourcing

Abstract

The project aims at contributing to the activities of COST Action CA 16105 - enetCollect - in the areas related to large-scale information extraction from the web and gamification of the preparation and the annotation of multimedia content suitable for various language learning activities. We will explore advanced methods for web-scale crawling and semantic enrichment of the collected material as well as modern human-computer interaction technologies engaging users in the process of acquisition of languages in the form of a game.

Team members

Smrž Pavel, doc. RNDr., Ph.D. (DCGM) – research leader
Najman Pavel, Ing. (DCGM)

Publications

2020

FAJČÍK, M.; DOČEKAL, M.; JON, J.; SMRŽ, P. BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models. In Proceedings of the Fourteenth Workshop on Semantic Evaluation. Barcelona (online): Association for Computational Linguistics, 2020. p. 437-444. ISBN: 978-1-952148-31-6. Detail