Mantas Lukoševičius is an associate professor at the KTU Faculty of Informatics and a researcher at the Institute of Biomedical Engineering. M. Lukoševičius’ activities are related to machine learning, biomedicine, image, and natural language signal processing and analysis.
The project goal achieved through modernization and development of the Lithuanian language syntactic and semantic analysis information system (LKSSAIS), modernization of existing and development of new public services for the tasks of written language recognition and electronic texts’ mining from various sources, as well as development of electronic tools (IT solutions) that would be made available for the reuse to electronic services/products developers.
Deep-Learning-Based Automatic Lithuanian Text Editor (Lituanistas)
The goal of this project was to create methodology of how the recent Transformer deep learning architecture can be employed for automatic text rewriting/editing. Model trained with pairs of flawed – correct text samples and in the end will be able to rewrite the given “illiterate” text into the correct one. It is the first one monolingual Transformer for Lithuanian language and will use a novel training data by messing text in a various level.
| No. | Title | Authors | Year |
| 1. | Efficient implementations of echo state network cross-validation | Mantas Lukoševičius, Arnas Uselis | 2021 |
| 2. | Testing pre-trained Transformer models for Lithuanian news clustering | Lukas Stankevičius, Mantas Lukoševičius | 2020 |
| 3. | Localized convolutional neural networks for geospatial wind forecasting | Arnas Uselis, Mantas Lukoševičius, Lukas Stasytis | 2020 |
| 4. | Frontiers in Reservoir Computing | Claudio Gallicchio, Mantas Lukoševicius, Simone Scardapane | 2020 |
| 5. | Accident localization at the district heating network of Kaunas Region using machine learning | Mantas Bukauskas, Mantas Lukoševičius | 2020 |
More scientific articles by Lukoševičius can be found here.
