228 citations
- Universidad Rey Juan CarlosES23 papers
- Center for Physical Sciences and TechnologyLT6 papers
- University of Maryland, College ParkUS4 papers
- Stanford UniversityUS3 papers
- Warsaw University of TechnologyPL3 papers
- Australian National UniversityAU2 papers
- Harvard UniversityUS2 papers
- Humboldt-Universität zu BerlinDE2 papers
- Institut de Sciences des Matériaux de MulhouseFR2 papers
- RMIT UniversityAU2 papers
- University of Colorado BoulderUS2 papers
- University of PisaIT2 papers
Showing cs.CLShow all
3 papers · 1 filter
cs.CL2024★ 29 cited
Extracting Sentence Embeddings from Pretrained Transformer Models
Lukas Stankevičius, Mantas Lukoševičius
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These se…
cs.CL2022★ 1 cited
Correcting diacritics and typos with a ByT5 transformer model
Lukas Stankevičius, Mantas Lukoševičius, Jurgita Kapočiūtė-Dzikienė +2
Due to the fast pace of life and online communications and the prevalence of English and the QWERTY keyboard, people tend to forgo using diacritics, make typographical errors (typo…
cs.CL2021
Generating abstractive summaries of Lithuanian news articles using a transformer model
Lukas Stankevičius, Mantas Lukoševičius
In this work, we train the first monolingual Lithuanian transformer model on a relatively large corpus of Lithuanian news articles and compare various output decoding algorithms fo…