@inproceedings{kwon-etal-2021-considering,
title = "Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer",
author = "Kwon, Jingun and
Kobayashi, Naoki and
Kamigaito, Hidetaka and
Okumura, Manabu",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.330",
doi = "10.18653/v1/2021.emnlp-main.330",
pages = "4039--4044",
abstract = "Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents. However, constructing a coherent and informative summary is difficult using a pre-trained BERT-based encoder since it is not explicitly trained for representing the information of sentences in a document. We propose a nested tree-based extractive summarization model on RoBERTa (NeRoBERTa), where nested tree structures consist of syntactic and discourse trees in a given document. Experimental results on the CNN/DailyMail dataset showed that NeRoBERTa outperforms baseline models in ROUGE. Human evaluation results also showed that NeRoBERTa achieves significantly better scores than the baselines in terms of coherence and yields comparable scores to the state-of-the-art models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kwon-etal-2021-considering">
<titleInfo>
<title>Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingun</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manabu</namePart>
<namePart type="family">Okumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents. However, constructing a coherent and informative summary is difficult using a pre-trained BERT-based encoder since it is not explicitly trained for representing the information of sentences in a document. We propose a nested tree-based extractive summarization model on RoBERTa (NeRoBERTa), where nested tree structures consist of syntactic and discourse trees in a given document. Experimental results on the CNN/DailyMail dataset showed that NeRoBERTa outperforms baseline models in ROUGE. Human evaluation results also showed that NeRoBERTa achieves significantly better scores than the baselines in terms of coherence and yields comparable scores to the state-of-the-art models.</abstract>
<identifier type="citekey">kwon-etal-2021-considering</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.330</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.330</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4039</start>
<end>4044</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer
%A Kwon, Jingun
%A Kobayashi, Naoki
%A Kamigaito, Hidetaka
%A Okumura, Manabu
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F kwon-etal-2021-considering
%X Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents. However, constructing a coherent and informative summary is difficult using a pre-trained BERT-based encoder since it is not explicitly trained for representing the information of sentences in a document. We propose a nested tree-based extractive summarization model on RoBERTa (NeRoBERTa), where nested tree structures consist of syntactic and discourse trees in a given document. Experimental results on the CNN/DailyMail dataset showed that NeRoBERTa outperforms baseline models in ROUGE. Human evaluation results also showed that NeRoBERTa achieves significantly better scores than the baselines in terms of coherence and yields comparable scores to the state-of-the-art models.
%R 10.18653/v1/2021.emnlp-main.330
%U https://aclanthology.org/2021.emnlp-main.330
%U https://doi.org/10.18653/v1/2021.emnlp-main.330
%P 4039-4044
Markdown (Informal)
[Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer](https://aclanthology.org/2021.emnlp-main.330) (Kwon et al., EMNLP 2021)
ACL