@inproceedings{jin-wan-2020-abstractive,
title = "Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization",
author = "Jin, Hanqi and
Wan, Xiaojun",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.231",
doi = "10.18653/v1/2020.findings-emnlp.231",
pages = "2545--2554",
abstract = "Single-document and multi-document summarizations are very closely related in both task definition and solution method. In this work, we propose to improve neural abstractive multi-document summarization by jointly learning an abstractive single-document summarizer. We build a unified model for single-document and multi-document summarizations by fully sharing the encoder and decoder and utilizing a decoding controller to aggregate the decoder{'}s outputs for multiple input documents. We evaluate our model on two multi-document summarization datasets: Multi-News and DUC-04. Experimental results show the efficacy of our approach, and it can substantially outperform several strong baselines. We also verify the helpfulness of single-document summarization to abstractive multi-document summarization task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-wan-2020-abstractive">
<titleInfo>
<title>Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanqi</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<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>Single-document and multi-document summarizations are very closely related in both task definition and solution method. In this work, we propose to improve neural abstractive multi-document summarization by jointly learning an abstractive single-document summarizer. We build a unified model for single-document and multi-document summarizations by fully sharing the encoder and decoder and utilizing a decoding controller to aggregate the decoder’s outputs for multiple input documents. We evaluate our model on two multi-document summarization datasets: Multi-News and DUC-04. Experimental results show the efficacy of our approach, and it can substantially outperform several strong baselines. We also verify the helpfulness of single-document summarization to abstractive multi-document summarization task.</abstract>
<identifier type="citekey">jin-wan-2020-abstractive</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.231</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.231</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2545</start>
<end>2554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization
%A Jin, Hanqi
%A Wan, Xiaojun
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jin-wan-2020-abstractive
%X Single-document and multi-document summarizations are very closely related in both task definition and solution method. In this work, we propose to improve neural abstractive multi-document summarization by jointly learning an abstractive single-document summarizer. We build a unified model for single-document and multi-document summarizations by fully sharing the encoder and decoder and utilizing a decoding controller to aggregate the decoder’s outputs for multiple input documents. We evaluate our model on two multi-document summarization datasets: Multi-News and DUC-04. Experimental results show the efficacy of our approach, and it can substantially outperform several strong baselines. We also verify the helpfulness of single-document summarization to abstractive multi-document summarization task.
%R 10.18653/v1/2020.findings-emnlp.231
%U https://aclanthology.org/2020.findings-emnlp.231
%U https://doi.org/10.18653/v1/2020.findings-emnlp.231
%P 2545-2554
Markdown (Informal)
[Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization](https://aclanthology.org/2020.findings-emnlp.231) (Jin & Wan, Findings 2020)
ACL