@inproceedings{gui-etal-2019-attention,
title = "Attention Optimization for Abstractive Document Summarization",
author = "Gui, Min and
Tian, Junfeng and
Wang, Rui and
Yang, Zhenglu",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1117/",
doi = "10.18653/v1/D19-1117",
pages = "1222--1228",
abstract = "Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models. To obtain a powerful attention helping with reproducing the most salient information and avoiding repetitions, we augment the vanilla attention model from both local and global aspects. We propose attention refinement unit paired with local variance loss to impose supervision on the attention model at each decoding step, and we also propose a global variance loss to optimize the attention distributions of all decoding steps from the global perspective. The performances on CNN/Daily Mail dataset verify the effectiveness of our methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gui-etal-2019-attention">
<titleInfo>
<title>Attention Optimization for Abstractive Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenglu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models. To obtain a powerful attention helping with reproducing the most salient information and avoiding repetitions, we augment the vanilla attention model from both local and global aspects. We propose attention refinement unit paired with local variance loss to impose supervision on the attention model at each decoding step, and we also propose a global variance loss to optimize the attention distributions of all decoding steps from the global perspective. The performances on CNN/Daily Mail dataset verify the effectiveness of our methods.</abstract>
<identifier type="citekey">gui-etal-2019-attention</identifier>
<identifier type="doi">10.18653/v1/D19-1117</identifier>
<location>
<url>https://aclanthology.org/D19-1117/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1222</start>
<end>1228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attention Optimization for Abstractive Document Summarization
%A Gui, Min
%A Tian, Junfeng
%A Wang, Rui
%A Yang, Zhenglu
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F gui-etal-2019-attention
%X Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models. To obtain a powerful attention helping with reproducing the most salient information and avoiding repetitions, we augment the vanilla attention model from both local and global aspects. We propose attention refinement unit paired with local variance loss to impose supervision on the attention model at each decoding step, and we also propose a global variance loss to optimize the attention distributions of all decoding steps from the global perspective. The performances on CNN/Daily Mail dataset verify the effectiveness of our methods.
%R 10.18653/v1/D19-1117
%U https://aclanthology.org/D19-1117/
%U https://doi.org/10.18653/v1/D19-1117
%P 1222-1228
Markdown (Informal)
[Attention Optimization for Abstractive Document Summarization](https://aclanthology.org/D19-1117/) (Gui et al., EMNLP-IJCNLP 2019)
ACL
- Min Gui, Junfeng Tian, Rui Wang, and Zhenglu Yang. 2019. Attention Optimization for Abstractive Document Summarization. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1222–1228, Hong Kong, China. Association for Computational Linguistics.