@inproceedings{loem-etal-2022-extraphrase,
title = "{E}xtra{P}hrase: Efficient Data Augmentation for Abstractive Summarization",
author = "Loem, Mengsay and
Takase, Sho and
Kaneko, Masahiro and
Okazaki, Naoaki",
editor = "Ippolito, Daphne and
Li, Liunian Harold and
Pacheco, Maria Leonor and
Chen, Danqi and
Xue, Nianwen",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-srw.3",
doi = "10.18653/v1/2022.naacl-srw.3",
pages = "16--24",
abstract = "Neural models trained with large amount of parallel data have achieved impressive performance in abstractive summarization tasks. However, large-scale parallel corpora are expensive and challenging to construct. In this work, we introduce a low-cost and effective strategy, ExtraPhrase, to augment training data for abstractive summarization tasks. ExtraPhrase constructs pseudo training data in two steps: extractive summarization and paraphrasing. We extract major parts of an input text in the extractive summarization step and obtain its diverse expressions with the paraphrasing step. Through experiments, we show that ExtraPhrase improves the performance of abstractive summarization tasks by more than 0.50 points in ROUGE scores compared to the setting without data augmentation. ExtraPhrase also outperforms existing methods such as back-translation and self-training. We also show that ExtraPhrase is significantly effective when the amount of genuine training data is remarkably small, i.e., a low-resource setting. Moreover, ExtraPhrase is more cost-efficient than the existing approaches",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="loem-etal-2022-extraphrase">
<titleInfo>
<title>ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengsay</namePart>
<namePart type="family">Loem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Takase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masahiro</namePart>
<namePart type="family">Kaneko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daphne</namePart>
<namePart type="family">Ippolito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liunian</namePart>
<namePart type="given">Harold</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural models trained with large amount of parallel data have achieved impressive performance in abstractive summarization tasks. However, large-scale parallel corpora are expensive and challenging to construct. In this work, we introduce a low-cost and effective strategy, ExtraPhrase, to augment training data for abstractive summarization tasks. ExtraPhrase constructs pseudo training data in two steps: extractive summarization and paraphrasing. We extract major parts of an input text in the extractive summarization step and obtain its diverse expressions with the paraphrasing step. Through experiments, we show that ExtraPhrase improves the performance of abstractive summarization tasks by more than 0.50 points in ROUGE scores compared to the setting without data augmentation. ExtraPhrase also outperforms existing methods such as back-translation and self-training. We also show that ExtraPhrase is significantly effective when the amount of genuine training data is remarkably small, i.e., a low-resource setting. Moreover, ExtraPhrase is more cost-efficient than the existing approaches</abstract>
<identifier type="citekey">loem-etal-2022-extraphrase</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-srw.3</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-srw.3</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>16</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization
%A Loem, Mengsay
%A Takase, Sho
%A Kaneko, Masahiro
%A Okazaki, Naoaki
%Y Ippolito, Daphne
%Y Li, Liunian Harold
%Y Pacheco, Maria Leonor
%Y Chen, Danqi
%Y Xue, Nianwen
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F loem-etal-2022-extraphrase
%X Neural models trained with large amount of parallel data have achieved impressive performance in abstractive summarization tasks. However, large-scale parallel corpora are expensive and challenging to construct. In this work, we introduce a low-cost and effective strategy, ExtraPhrase, to augment training data for abstractive summarization tasks. ExtraPhrase constructs pseudo training data in two steps: extractive summarization and paraphrasing. We extract major parts of an input text in the extractive summarization step and obtain its diverse expressions with the paraphrasing step. Through experiments, we show that ExtraPhrase improves the performance of abstractive summarization tasks by more than 0.50 points in ROUGE scores compared to the setting without data augmentation. ExtraPhrase also outperforms existing methods such as back-translation and self-training. We also show that ExtraPhrase is significantly effective when the amount of genuine training data is remarkably small, i.e., a low-resource setting. Moreover, ExtraPhrase is more cost-efficient than the existing approaches
%R 10.18653/v1/2022.naacl-srw.3
%U https://aclanthology.org/2022.naacl-srw.3
%U https://doi.org/10.18653/v1/2022.naacl-srw.3
%P 16-24
Markdown (Informal)
[ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization](https://aclanthology.org/2022.naacl-srw.3) (Loem et al., NAACL 2022)
ACL
- Mengsay Loem, Sho Takase, Masahiro Kaneko, and Naoaki Okazaki. 2022. ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 16–24, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.