Generating abstractive summaries of Lithuanian news articles using a transformer model
Computation and Language
2021-10-19 v2 Information Retrieval
Machine Learning
Abstract
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 for abstractive news summarization. We achieve an average ROUGE-2 score 0.163, generated summaries are coherent and look impressive at first glance. However, some of them contain misleading information that is not so easy to spot. We describe all the technical details and share our trained model and accompanying code in an online open-source repository, as well as some characteristic samples of the generated summaries.
Keywords
Cite
@article{arxiv.2105.03279,
title = {Generating abstractive summaries of Lithuanian news articles using a transformer model},
author = {Lukas Stankevičius and Mantas Lukoševičius},
journal= {arXiv preprint arXiv:2105.03279},
year = {2021}
}
Comments
Accepted in ICIST 2021