@inproceedings{qiu-cohen-2022-abstractive,
title = "Abstractive Summarization Guided by Latent Hierarchical Document Structure",
author = "Qiu, Yifu and
Cohen, Shay B.",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.355",
doi = "10.18653/v1/2022.emnlp-main.355",
pages = "5303--5317",
abstract = "Sequential abstractive neural summarizers often do not use the underlying structure in the input article or dependencies between the input sentences. This structure is essential to integrate and consolidate information from different parts of the text. To address this shortcoming, we propose a hierarchy-aware graph neural network (HierGNN) which captures such dependencies through three main steps: 1) learning a hierarchical document structure through a latent structure tree learned by a sparse matrix-tree computation; 2) propagating sentence information over this structure using a novel message-passing node propagation mechanism to identify salient information; 3) using graph-level attention to concentrate the decoder on salient information. Experiments confirm HierGNN improves strong sequence models such as BART, with a 0.55 and 0.75 margin in average ROUGE-1/2/L for CNN/DM and XSum. Further human evaluation demonstrates that summaries produced by our model are more relevant and less redundant than the baselines, into which HierGNN is incorporated. We also find HierGNN synthesizes summaries by fusing multiple source sentences more, rather than compressing a single source sentence, and that it processes long inputs more effectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-cohen-2022-abstractive">
<titleInfo>
<title>Abstractive Summarization Guided by Latent Hierarchical Document Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifu</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequential abstractive neural summarizers often do not use the underlying structure in the input article or dependencies between the input sentences. This structure is essential to integrate and consolidate information from different parts of the text. To address this shortcoming, we propose a hierarchy-aware graph neural network (HierGNN) which captures such dependencies through three main steps: 1) learning a hierarchical document structure through a latent structure tree learned by a sparse matrix-tree computation; 2) propagating sentence information over this structure using a novel message-passing node propagation mechanism to identify salient information; 3) using graph-level attention to concentrate the decoder on salient information. Experiments confirm HierGNN improves strong sequence models such as BART, with a 0.55 and 0.75 margin in average ROUGE-1/2/L for CNN/DM and XSum. Further human evaluation demonstrates that summaries produced by our model are more relevant and less redundant than the baselines, into which HierGNN is incorporated. We also find HierGNN synthesizes summaries by fusing multiple source sentences more, rather than compressing a single source sentence, and that it processes long inputs more effectively.</abstract>
<identifier type="citekey">qiu-cohen-2022-abstractive</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.355</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.355</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5303</start>
<end>5317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abstractive Summarization Guided by Latent Hierarchical Document Structure
%A Qiu, Yifu
%A Cohen, Shay B.
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F qiu-cohen-2022-abstractive
%X Sequential abstractive neural summarizers often do not use the underlying structure in the input article or dependencies between the input sentences. This structure is essential to integrate and consolidate information from different parts of the text. To address this shortcoming, we propose a hierarchy-aware graph neural network (HierGNN) which captures such dependencies through three main steps: 1) learning a hierarchical document structure through a latent structure tree learned by a sparse matrix-tree computation; 2) propagating sentence information over this structure using a novel message-passing node propagation mechanism to identify salient information; 3) using graph-level attention to concentrate the decoder on salient information. Experiments confirm HierGNN improves strong sequence models such as BART, with a 0.55 and 0.75 margin in average ROUGE-1/2/L for CNN/DM and XSum. Further human evaluation demonstrates that summaries produced by our model are more relevant and less redundant than the baselines, into which HierGNN is incorporated. We also find HierGNN synthesizes summaries by fusing multiple source sentences more, rather than compressing a single source sentence, and that it processes long inputs more effectively.
%R 10.18653/v1/2022.emnlp-main.355
%U https://aclanthology.org/2022.emnlp-main.355
%U https://doi.org/10.18653/v1/2022.emnlp-main.355
%P 5303-5317
Markdown (Informal)
[Abstractive Summarization Guided by Latent Hierarchical Document Structure](https://aclanthology.org/2022.emnlp-main.355) (Qiu & Cohen, EMNLP 2022)
ACL