29 citations · 35 across the 5 of their papers we have counts for
5 papers
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…
Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models
Brigita Vileikytė, Mantas Lukoševičius, Lukas Stankevičius
Sentiment analysis is a widely researched area within Natural Language Processing (NLP), attracting significant interest due to the advent of automated solutions. Despite this, the…
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…
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…
Testing pre-trained Transformer models for Lithuanian news clustering
Lukas Stankevičius, Mantas Lukoševičius
A recent introduction of Transformer deep learning architecture made breakthroughs in various natural language processing tasks. However, non-English languages could not leverage s…