@inproceedings{galeshchuk-2023-abstractive,
title = "Abstractive Summarization for the {U}krainian Language: Multi-Task Learning with Hromadske.ua News Dataset",
author = "Galeshchuk, Svitlana",
editor = "Romanyshyn, Mariana",
booktitle = "Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.unlp-1.6",
doi = "10.18653/v1/2023.unlp-1.6",
pages = "49--53",
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 r{\'e}sum{\'e}. 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galeshchuk-2023-abstractive">
<titleInfo>
<title>Abstractive Summarization for the Ukrainian Language: Multi-Task Learning with Hromadske.ua News Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svitlana</namePart>
<namePart type="family">Galeshchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">galeshchuk-2023-abstractive</identifier>
<identifier type="doi">10.18653/v1/2023.unlp-1.6</identifier>
<location>
<url>https://aclanthology.org/2023.unlp-1.6</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>49</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abstractive Summarization for the Ukrainian Language: Multi-Task Learning with Hromadske.ua News Dataset
%A Galeshchuk, Svitlana
%Y Romanyshyn, Mariana
%S Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F galeshchuk-2023-abstractive
%X 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.
%R 10.18653/v1/2023.unlp-1.6
%U https://aclanthology.org/2023.unlp-1.6
%U https://doi.org/10.18653/v1/2023.unlp-1.6
%P 49-53
Markdown (Informal)
[Abstractive Summarization for the Ukrainian Language: Multi-Task Learning with Hromadske.ua News Dataset](https://aclanthology.org/2023.unlp-1.6) (Galeshchuk, UNLP 2023)
ACL