Abstract
Despite recent NLP developments, abstractive summarization remains a challenging task, especially in the case of low-resource languages like Ukrainian. The paper aims at improving the quality of summaries produced by mT5 for news in Ukrainian by fine-tuning the model with a mixture of summarization and text similarity tasks using summary-article and title-article training pairs, respectively. The proposed training set-up with small, base, and large mT5 models produce higher quality résumé. Besides, we present a new Ukrainian dataset for the abstractive summarization task that consists of circa 36.5K articles collected from Hromadske.ua until June 2021.- Anthology ID:
- 2023.unlp-1.6
- Volume:
- Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editor:
- Mariana Romanyshyn
- Venue:
- UNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 49–53
- Language:
- URL:
- https://aclanthology.org/2023.unlp-1.6
- DOI:
- 10.18653/v1/2023.unlp-1.6
- Cite (ACL):
- Svitlana Galeshchuk. 2023. Abstractive Summarization for the Ukrainian Language: Multi-Task Learning with Hromadske.ua News Dataset. In Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP), pages 49–53, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Abstractive Summarization for the Ukrainian Language: Multi-Task Learning with Hromadske.ua News Dataset (Galeshchuk, UNLP 2023)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2023.unlp-1.6.pdf