TL;DR
This paper introduces the first Lithuanian transformer model for abstractive news summarization, demonstrating promising results but also highlighting challenges with factual accuracy.
Contribution
It presents the development and evaluation of the first monolingual Lithuanian transformer model for news summarization, including analysis of decoding algorithms and sharing of resources.
Findings
Achieved an average ROUGE-2 score of 0.163
Generated summaries are coherent and visually impressive
Some summaries contain misleading information
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
