@inproceedings{kryscinski-etal-2018-improving,
title = "Improving Abstraction in Text Summarization",
author = "Kry{\'s}ci{\'n}ski, Wojciech and
Paulus, Romain and
Xiong, Caiming and
Socher, Richard",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1207",
doi = "10.18653/v1/D18-1207",
pages = "1808--1817",
abstract = "Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do not appear in the source document remains low in existing approaches. We propose two techniques to improve the level of abstraction of generated summaries. First, we decompose the decoder into a contextual network that retrieves relevant parts of the source document, and a pretrained language model that incorporates prior knowledge about language generation. Second, we propose a novelty metric that is optimized directly through policy learning to encourage the generation of novel phrases. Our model achieves results comparable to state-of-the-art models, as determined by ROUGE scores and human evaluations, while achieving a significantly higher level of abstraction as measured by n-gram overlap with the source document.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kryscinski-etal-2018-improving">
<titleInfo>
<title>Improving Abstraction in Text Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wojciech</namePart>
<namePart type="family">Kryściński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romain</namePart>
<namePart type="family">Paulus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Socher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do not appear in the source document remains low in existing approaches. We propose two techniques to improve the level of abstraction of generated summaries. First, we decompose the decoder into a contextual network that retrieves relevant parts of the source document, and a pretrained language model that incorporates prior knowledge about language generation. Second, we propose a novelty metric that is optimized directly through policy learning to encourage the generation of novel phrases. Our model achieves results comparable to state-of-the-art models, as determined by ROUGE scores and human evaluations, while achieving a significantly higher level of abstraction as measured by n-gram overlap with the source document.</abstract>
<identifier type="citekey">kryscinski-etal-2018-improving</identifier>
<identifier type="doi">10.18653/v1/D18-1207</identifier>
<location>
<url>https://aclanthology.org/D18-1207</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>1808</start>
<end>1817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Abstraction in Text Summarization
%A Kryściński, Wojciech
%A Paulus, Romain
%A Xiong, Caiming
%A Socher, Richard
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F kryscinski-etal-2018-improving
%X Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do not appear in the source document remains low in existing approaches. We propose two techniques to improve the level of abstraction of generated summaries. First, we decompose the decoder into a contextual network that retrieves relevant parts of the source document, and a pretrained language model that incorporates prior knowledge about language generation. Second, we propose a novelty metric that is optimized directly through policy learning to encourage the generation of novel phrases. Our model achieves results comparable to state-of-the-art models, as determined by ROUGE scores and human evaluations, while achieving a significantly higher level of abstraction as measured by n-gram overlap with the source document.
%R 10.18653/v1/D18-1207
%U https://aclanthology.org/D18-1207
%U https://doi.org/10.18653/v1/D18-1207
%P 1808-1817
Markdown (Informal)
[Improving Abstraction in Text Summarization](https://aclanthology.org/D18-1207) (Kryściński et al., EMNLP 2018)
ACL
- Wojciech Kryściński, Romain Paulus, Caiming Xiong, and Richard Socher. 2018. Improving Abstraction in Text Summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1808–1817, Brussels, Belgium. Association for Computational Linguistics.