@inproceedings{you-etal-2019-improving,
title = "Improving Abstractive Document Summarization with Salient Information Modeling",
author = "You, Yongjian and
Jia, Weijia and
Liu, Tianyi and
Yang, Wenmian",
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/P19-1205",
doi = "10.18653/v1/P19-1205",
pages = "2132--2141",
abstract = "Comprehensive document encoding and salient information selection are two major difficulties for generating summaries with adequate salient information. To tackle the above difficulties, we propose a Transformer-based encoder-decoder framework with two novel extensions for abstractive document summarization. Specifically, (1) to encode the documents comprehensively, we design a focus-attention mechanism and incorporate it into the encoder. This mechanism models a Gaussian focal bias on attention scores to enhance the perception of local context, which contributes to producing salient and informative summaries. (2) To distinguish salient information precisely, we design an independent saliency-selection network which manages the information flow from encoder to decoder. This network effectively reduces the influences of secondary information on the generated summaries. Experimental results on the popular CNN/Daily Mail benchmark demonstrate that our model outperforms other state-of-the-art baselines on the ROUGE metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="you-etal-2019-improving">
<titleInfo>
<title>Improving Abstractive Document Summarization with Salient Information Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongjian</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenmian</namePart>
<namePart type="family">Yang</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>Comprehensive document encoding and salient information selection are two major difficulties for generating summaries with adequate salient information. To tackle the above difficulties, we propose a Transformer-based encoder-decoder framework with two novel extensions for abstractive document summarization. Specifically, (1) to encode the documents comprehensively, we design a focus-attention mechanism and incorporate it into the encoder. This mechanism models a Gaussian focal bias on attention scores to enhance the perception of local context, which contributes to producing salient and informative summaries. (2) To distinguish salient information precisely, we design an independent saliency-selection network which manages the information flow from encoder to decoder. This network effectively reduces the influences of secondary information on the generated summaries. Experimental results on the popular CNN/Daily Mail benchmark demonstrate that our model outperforms other state-of-the-art baselines on the ROUGE metrics.</abstract>
<identifier type="citekey">you-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/P19-1205</identifier>
<location>
<url>https://aclanthology.org/P19-1205</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>2132</start>
<end>2141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Abstractive Document Summarization with Salient Information Modeling
%A You, Yongjian
%A Jia, Weijia
%A Liu, Tianyi
%A Yang, Wenmian
%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 you-etal-2019-improving
%X Comprehensive document encoding and salient information selection are two major difficulties for generating summaries with adequate salient information. To tackle the above difficulties, we propose a Transformer-based encoder-decoder framework with two novel extensions for abstractive document summarization. Specifically, (1) to encode the documents comprehensively, we design a focus-attention mechanism and incorporate it into the encoder. This mechanism models a Gaussian focal bias on attention scores to enhance the perception of local context, which contributes to producing salient and informative summaries. (2) To distinguish salient information precisely, we design an independent saliency-selection network which manages the information flow from encoder to decoder. This network effectively reduces the influences of secondary information on the generated summaries. Experimental results on the popular CNN/Daily Mail benchmark demonstrate that our model outperforms other state-of-the-art baselines on the ROUGE metrics.
%R 10.18653/v1/P19-1205
%U https://aclanthology.org/P19-1205
%U https://doi.org/10.18653/v1/P19-1205
%P 2132-2141
Markdown (Informal)
[Improving Abstractive Document Summarization with Salient Information Modeling](https://aclanthology.org/P19-1205) (You et al., ACL 2019)
ACL