@inproceedings{lu-etal-2020-multi-xscience,
title = "Multi-{XS}cience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles",
author = "Lu, Yao and
Dong, Yue and
Charlin, Laurent",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.648",
doi = "10.18653/v1/2020.emnlp-main.648",
pages = "8068--8074",
abstract = "Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results{---}using several state-of-the-art models trained on the Multi-XScience dataset{---}reveal that Multi-XScience is well suited for abstractive models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2020-multi-xscience">
<titleInfo>
<title>Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Charlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results—using several state-of-the-art models trained on the Multi-XScience dataset—reveal that Multi-XScience is well suited for abstractive models.</abstract>
<identifier type="citekey">lu-etal-2020-multi-xscience</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.648</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.648</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8068</start>
<end>8074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles
%A Lu, Yao
%A Dong, Yue
%A Charlin, Laurent
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lu-etal-2020-multi-xscience
%X Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results—using several state-of-the-art models trained on the Multi-XScience dataset—reveal that Multi-XScience is well suited for abstractive models.
%R 10.18653/v1/2020.emnlp-main.648
%U https://aclanthology.org/2020.emnlp-main.648
%U https://doi.org/10.18653/v1/2020.emnlp-main.648
%P 8068-8074
Markdown (Informal)
[Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://aclanthology.org/2020.emnlp-main.648) (Lu et al., EMNLP 2020)
ACL