@inproceedings{ma-etal-2024-prom,
title = "{PROM}: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization",
author = "Ma, Xinbei and
Gong, Yeyun and
He, Pengcheng and
Zhao, Hai and
Duan, Nan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1148",
pages = "13103--13119",
abstract = "Based on the remarkable achievements of pre-trained language models in abstractive summarization, the copying mechanism has proved helpful by improving the factuality, stability, and overall performance. This work proposes PROM, a new PhRase-level cOpying Mechanism that enhances attention on n-grams, which can be applied to zero-shot summarization with pre-training. PROM adds an indicator layer to explicitly pick up tokens in n-gram that can be copied from the source, and calculates an auxiliary loss for the copying prediction. Empirical studies show that PROM makes significant improvements in fine-tuning on benchmarks. In the zero-shot setting, PROM is utilized in the self-supervised pre-training on raw corpora and provides new general baselines on a wide range of summarization datasets. Further analysis shows that PROM performs more reasonable copying and contributes to faithfulness. Our code is publicly available at https://github.com/xbmxb/PROM.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2024-prom">
<titleInfo>
<title>PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinbei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Based on the remarkable achievements of pre-trained language models in abstractive summarization, the copying mechanism has proved helpful by improving the factuality, stability, and overall performance. This work proposes PROM, a new PhRase-level cOpying Mechanism that enhances attention on n-grams, which can be applied to zero-shot summarization with pre-training. PROM adds an indicator layer to explicitly pick up tokens in n-gram that can be copied from the source, and calculates an auxiliary loss for the copying prediction. Empirical studies show that PROM makes significant improvements in fine-tuning on benchmarks. In the zero-shot setting, PROM is utilized in the self-supervised pre-training on raw corpora and provides new general baselines on a wide range of summarization datasets. Further analysis shows that PROM performs more reasonable copying and contributes to faithfulness. Our code is publicly available at https://github.com/xbmxb/PROM.</abstract>
<identifier type="citekey">ma-etal-2024-prom</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1148</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13103</start>
<end>13119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization
%A Ma, Xinbei
%A Gong, Yeyun
%A He, Pengcheng
%A Zhao, Hai
%A Duan, Nan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ma-etal-2024-prom
%X Based on the remarkable achievements of pre-trained language models in abstractive summarization, the copying mechanism has proved helpful by improving the factuality, stability, and overall performance. This work proposes PROM, a new PhRase-level cOpying Mechanism that enhances attention on n-grams, which can be applied to zero-shot summarization with pre-training. PROM adds an indicator layer to explicitly pick up tokens in n-gram that can be copied from the source, and calculates an auxiliary loss for the copying prediction. Empirical studies show that PROM makes significant improvements in fine-tuning on benchmarks. In the zero-shot setting, PROM is utilized in the self-supervised pre-training on raw corpora and provides new general baselines on a wide range of summarization datasets. Further analysis shows that PROM performs more reasonable copying and contributes to faithfulness. Our code is publicly available at https://github.com/xbmxb/PROM.
%U https://aclanthology.org/2024.lrec-main.1148
%P 13103-13119
Markdown (Informal)
[PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization](https://aclanthology.org/2024.lrec-main.1148) (Ma et al., LREC-COLING 2024)
ACL