@inproceedings{pasunuru-etal-2021-efficiently,
title = "Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters",
author = "Pasunuru, Ramakanth and
Liu, Mengwen and
Bansal, Mohit and
Ravi, Sujith and
Dreyer, Markus",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.380",
doi = "10.18653/v1/2021.naacl-main.380",
pages = "4768--4779",
abstract = "This paper presents an efficient graph-enhanced approach to multi-document summarization (MDS) with an encoder-decoder Transformer model. This model is based on recent advances in pre-training both encoder and decoder on very large text data (Lewis et al., 2019), and it incorporates an efficient encoding mechanism (Beltagy et al., 2020) that avoids the quadratic memory growth typical for traditional Transformers. We show that this powerful combination not only scales to large input documents commonly found when summarizing news clusters; it also enables us to process additional input in the form of auxiliary graph representations, which we derive from the multi-document clusters. We present a mechanism to incorporate such graph information into the encoder-decoder model that was pre-trained on text only. Our approach leads to significant improvements on the Multi-News dataset, overall leading to an average 1.8 ROUGE score improvement over previous work (Li et al., 2020). We also show improvements in a transfer-only setup on the DUC-2004 dataset. The graph encodings lead to summaries that are more abstractive. Human evaluation shows that they are also more informative and factually more consistent with their input documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pasunuru-etal-2021-efficiently">
<titleInfo>
<title>Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramakanth</namePart>
<namePart type="family">Pasunuru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengwen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujith</namePart>
<namePart type="family">Ravi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Dreyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an efficient graph-enhanced approach to multi-document summarization (MDS) with an encoder-decoder Transformer model. This model is based on recent advances in pre-training both encoder and decoder on very large text data (Lewis et al., 2019), and it incorporates an efficient encoding mechanism (Beltagy et al., 2020) that avoids the quadratic memory growth typical for traditional Transformers. We show that this powerful combination not only scales to large input documents commonly found when summarizing news clusters; it also enables us to process additional input in the form of auxiliary graph representations, which we derive from the multi-document clusters. We present a mechanism to incorporate such graph information into the encoder-decoder model that was pre-trained on text only. Our approach leads to significant improvements on the Multi-News dataset, overall leading to an average 1.8 ROUGE score improvement over previous work (Li et al., 2020). We also show improvements in a transfer-only setup on the DUC-2004 dataset. The graph encodings lead to summaries that are more abstractive. Human evaluation shows that they are also more informative and factually more consistent with their input documents.</abstract>
<identifier type="citekey">pasunuru-etal-2021-efficiently</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.380</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.380</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4768</start>
<end>4779</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters
%A Pasunuru, Ramakanth
%A Liu, Mengwen
%A Bansal, Mohit
%A Ravi, Sujith
%A Dreyer, Markus
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F pasunuru-etal-2021-efficiently
%X This paper presents an efficient graph-enhanced approach to multi-document summarization (MDS) with an encoder-decoder Transformer model. This model is based on recent advances in pre-training both encoder and decoder on very large text data (Lewis et al., 2019), and it incorporates an efficient encoding mechanism (Beltagy et al., 2020) that avoids the quadratic memory growth typical for traditional Transformers. We show that this powerful combination not only scales to large input documents commonly found when summarizing news clusters; it also enables us to process additional input in the form of auxiliary graph representations, which we derive from the multi-document clusters. We present a mechanism to incorporate such graph information into the encoder-decoder model that was pre-trained on text only. Our approach leads to significant improvements on the Multi-News dataset, overall leading to an average 1.8 ROUGE score improvement over previous work (Li et al., 2020). We also show improvements in a transfer-only setup on the DUC-2004 dataset. The graph encodings lead to summaries that are more abstractive. Human evaluation shows that they are also more informative and factually more consistent with their input documents.
%R 10.18653/v1/2021.naacl-main.380
%U https://aclanthology.org/2021.naacl-main.380
%U https://doi.org/10.18653/v1/2021.naacl-main.380
%P 4768-4779
Markdown (Informal)
[Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters](https://aclanthology.org/2021.naacl-main.380) (Pasunuru et al., NAACL 2021)
ACL
- Ramakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, and Markus Dreyer. 2021. Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4768–4779, Online. Association for Computational Linguistics.