@inproceedings{mondshine-etal-2024-hesum,
title = "{H}e{S}um: a Novel Dataset for Abstractive Text Summarization in {H}ebrew",
author = "Mondshine, Itai and
Paz-Argaman, Tzuf and
Achi Mordechai, Asaf and
Tsarfaty, Reut",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.loresmt-1.2",
doi = "10.18653/v1/2024.loresmt-1.2",
pages = "26--36",
abstract = "While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction. In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum{'}s high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondshine-etal-2024-hesum">
<titleInfo>
<title>HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew</title>
</titleInfo>
<name type="personal">
<namePart type="given">Itai</namePart>
<namePart type="family">Mondshine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tzuf</namePart>
<namePart type="family">Paz-Argaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asaf</namePart>
<namePart type="family">Achi Mordechai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction. In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum’s high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.</abstract>
<identifier type="citekey">mondshine-etal-2024-hesum</identifier>
<identifier type="doi">10.18653/v1/2024.loresmt-1.2</identifier>
<location>
<url>https://aclanthology.org/2024.loresmt-1.2</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>26</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew
%A Mondshine, Itai
%A Paz-Argaman, Tzuf
%A Achi Mordechai, Asaf
%A Tsarfaty, Reut
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mondshine-etal-2024-hesum
%X While large language models (LLMs) excel in various natural language tasks in English, their performance in low-resource languages like Hebrew, especially for generative tasks such as abstractive summarization, remains unclear. The high morphological richness in Hebrew adds further challenges due to the ambiguity in sentence comprehension and the complexities in meaning construction. In this paper, we address this evaluation and resource gap by introducing HeSum, a novel benchmark dataset specifically designed for Hebrew abstractive text summarization. HeSum consists of 10,000 article-summary pairs sourced from Hebrew news websites written by professionals. Linguistic analysis confirms HeSum’s high abstractness and unique morphological challenges. We show that HeSum presents distinct difficulties even for state-of-the-art LLMs, establishing it as a valuable testbed for advancing generative language technology in Hebrew, and MRLs generative challenges in general.
%R 10.18653/v1/2024.loresmt-1.2
%U https://aclanthology.org/2024.loresmt-1.2
%U https://doi.org/10.18653/v1/2024.loresmt-1.2
%P 26-36
Markdown (Informal)
[HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew](https://aclanthology.org/2024.loresmt-1.2) (Mondshine et al., LoResMT-WS 2024)
ACL
- Itai Mondshine, Tzuf Paz-Argaman, Asaf Achi Mordechai, and Reut Tsarfaty. 2024. HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew. In Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), pages 26–36, Bangkok, Thailand. Association for Computational Linguistics.