@inproceedings{dadason-etal-2021-icesum,
title = "{I}ce{S}um: An {I}celandic Text Summarization Corpus",
author = {Da{\dh}ason, J{\'o}n and
Loftsson, Hrafn and
Sigur{\dh}ard{\'o}ttir, Salome and
Bj{\"o}rnsson, {\TH}orsteinn},
editor = "Durmus, Esin and
Gupta, Vivek and
Liu, Nelson and
Peng, Nanyun and
Su, Yu",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-srw.2",
doi = "10.18653/v1/2021.naacl-srw.2",
pages = "9--14",
abstract = "Automatic Text Summarization (ATS) is the task of generating concise and fluent summaries from one or more documents. In this paper, we present IceSum, the first Icelandic corpus annotated with human-generated summaries. IceSum consists of 1,000 online news articles and their extractive summaries. We train and evaluate several neural network-based models on this dataset, comparing them against a selection of baseline methods. We find that an encoder-decoder model with a sequence-to-sequence based extractor obtains the best results, outperforming all baseline methods. Furthermore, we evaluate how the size of the training corpus affects the quality of the generated summaries. We release the corpus and the models with an open license.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dadason-etal-2021-icesum">
<titleInfo>
<title>IceSum: An Icelandic Text Summarization Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="family">Da\dhason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salome</namePart>
<namePart type="family">Sigur\dhardóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">\THorsteinn</namePart>
<namePart type="family">Björnsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esin</namePart>
<namePart type="family">Durmus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Text Summarization (ATS) is the task of generating concise and fluent summaries from one or more documents. In this paper, we present IceSum, the first Icelandic corpus annotated with human-generated summaries. IceSum consists of 1,000 online news articles and their extractive summaries. We train and evaluate several neural network-based models on this dataset, comparing them against a selection of baseline methods. We find that an encoder-decoder model with a sequence-to-sequence based extractor obtains the best results, outperforming all baseline methods. Furthermore, we evaluate how the size of the training corpus affects the quality of the generated summaries. We release the corpus and the models with an open license.</abstract>
<identifier type="citekey">dadason-etal-2021-icesum</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-srw.2</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-srw.2</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>9</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IceSum: An Icelandic Text Summarization Corpus
%A Da\dhason, Jón
%A Loftsson, Hrafn
%A Sigur\dhardóttir, Salome
%A Björnsson, \THorsteinn
%Y Durmus, Esin
%Y Gupta, Vivek
%Y Liu, Nelson
%Y Peng, Nanyun
%Y Su, Yu
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F dadason-etal-2021-icesum
%X Automatic Text Summarization (ATS) is the task of generating concise and fluent summaries from one or more documents. In this paper, we present IceSum, the first Icelandic corpus annotated with human-generated summaries. IceSum consists of 1,000 online news articles and their extractive summaries. We train and evaluate several neural network-based models on this dataset, comparing them against a selection of baseline methods. We find that an encoder-decoder model with a sequence-to-sequence based extractor obtains the best results, outperforming all baseline methods. Furthermore, we evaluate how the size of the training corpus affects the quality of the generated summaries. We release the corpus and the models with an open license.
%R 10.18653/v1/2021.naacl-srw.2
%U https://aclanthology.org/2021.naacl-srw.2
%U https://doi.org/10.18653/v1/2021.naacl-srw.2
%P 9-14
Markdown (Informal)
[IceSum: An Icelandic Text Summarization Corpus](https://aclanthology.org/2021.naacl-srw.2) (Daðason et al., NAACL 2021)
ACL
- Jón Daðason, Hrafn Loftsson, Salome Sigurðardóttir, and Þorsteinn Björnsson. 2021. IceSum: An Icelandic Text Summarization Corpus. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 9–14, Online. Association for Computational Linguistics.