@inproceedings{cho-etal-2019-improving,
title = "Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization",
author = "Cho, Sangwoo and
Lebanoff, Logan and
Foroosh, Hassan and
Liu, Fei",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1098",
doi = "10.18653/v1/P19-1098",
pages = "1027--1038",
abstract = "The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but optimization-based methods such as determinantal point processes (DPPs) are known to handle them well. In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks. The approach measures redundancy between a pair of sentences based on surface form and semantic information. We show that our DPP system with improved similarity measure performs competitively, outperforming strong summarization baselines on benchmark datasets. Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2019-improving">
<titleInfo>
<title>Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sangwoo</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Logan</namePart>
<namePart type="family">Lebanoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Foroosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but optimization-based methods such as determinantal point processes (DPPs) are known to handle them well. In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks. The approach measures redundancy between a pair of sentences based on surface form and semantic information. We show that our DPP system with improved similarity measure performs competitively, outperforming strong summarization baselines on benchmark datasets. Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions.</abstract>
<identifier type="citekey">cho-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/P19-1098</identifier>
<location>
<url>https://aclanthology.org/P19-1098</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>1027</start>
<end>1038</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
%A Cho, Sangwoo
%A Lebanoff, Logan
%A Foroosh, Hassan
%A Liu, Fei
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F cho-etal-2019-improving
%X The most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but optimization-based methods such as determinantal point processes (DPPs) are known to handle them well. In this paper we seek to strengthen a DPP-based method for extractive multi-document summarization by presenting a novel similarity measure inspired by capsule networks. The approach measures redundancy between a pair of sentences based on surface form and semantic information. We show that our DPP system with improved similarity measure performs competitively, outperforming strong summarization baselines on benchmark datasets. Our findings are particularly meaningful for summarizing documents created by multiple authors containing redundant yet lexically diverse expressions.
%R 10.18653/v1/P19-1098
%U https://aclanthology.org/P19-1098
%U https://doi.org/10.18653/v1/P19-1098
%P 1027-1038
Markdown (Informal)
[Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization](https://aclanthology.org/P19-1098) (Cho et al., ACL 2019)
ACL