@inproceedings{bae-etal-2019-summary,
title = "Summary Level Training of Sentence Rewriting for Abstractive Summarization",
author = "Bae, Sanghwan and
Kim, Taeuk and
Kim, Jihoon and
Lee, Sang-goo",
editor = "Wang, Lu and
Cheung, Jackie Chi Kit and
Carenini, Giuseppe and
Liu, Fei",
booktitle = "Proceedings of the 2nd Workshop on New Frontiers in Summarization",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5402/",
doi = "10.18653/v1/D19-5402",
pages = "10--20",
abstract = "As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bae-etal-2019-summary">
<titleInfo>
<title>Summary Level Training of Sentence Rewriting for Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanghwan</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taeuk</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang-goo</namePart>
<namePart type="family">Lee</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 2nd Workshop on New Frontiers in Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackie</namePart>
<namePart type="given">Chi</namePart>
<namePart type="given">Kit</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</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>As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set.</abstract>
<identifier type="citekey">bae-etal-2019-summary</identifier>
<identifier type="doi">10.18653/v1/D19-5402</identifier>
<location>
<url>https://aclanthology.org/D19-5402/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>10</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Summary Level Training of Sentence Rewriting for Abstractive Summarization
%A Bae, Sanghwan
%A Kim, Taeuk
%A Kim, Jihoon
%A Lee, Sang-goo
%Y Wang, Lu
%Y Cheung, Jackie Chi Kit
%Y Carenini, Giuseppe
%Y Liu, Fei
%S Proceedings of the 2nd Workshop on New Frontiers in Summarization
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F bae-etal-2019-summary
%X As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set.
%R 10.18653/v1/D19-5402
%U https://aclanthology.org/D19-5402/
%U https://doi.org/10.18653/v1/D19-5402
%P 10-20
Markdown (Informal)
[Summary Level Training of Sentence Rewriting for Abstractive Summarization](https://aclanthology.org/D19-5402/) (Bae et al., 2019)
- Summary Level Training of Sentence Rewriting for Abstractive Summarization (Bae et al., 2019)
ACL
- Sanghwan Bae, Taeuk Kim, Jihoon Kim, and Sang-goo Lee. 2019. Summary Level Training of Sentence Rewriting for Abstractive Summarization. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 10–20, Hong Kong, China. Association for Computational Linguistics.