@inproceedings{liu-etal-2024-p3sum,
title = "{P}$^3${S}um: Preserving Author{'}s Perspective in News Summarization with Diffusion Language Models",
author = "Liu, Yuhan and
Feng, Shangbin and
Han, Xiaochuang and
Balachandran, Vidhisha and
Park, Chan Young and
Kumar, Sachin and
Tsvetkov, Yulia",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.119",
doi = "10.18653/v1/2024.naacl-long.119",
pages = "2154--2173",
abstract = "In this work, we take a first step towards designing summarization systems that are faithful to the author{'}s intent, not only the semantic content of the article. Focusing on a case study of preserving political perspectives in news summarization, we find that existing approaches alter the political opinions and stances of news articles in more than 50{\%} of summaries, misrepresenting the intent and perspectives of the news authors. We thus propose P$^3$Sum, a diffusion model-based summarization approach controlled by political perspective classifiers. In P$^3$Sum, the political leaning of a generated summary is iteratively evaluated at each decoding step, and any drift from the article{'}s original stance incurs a loss back-propagated to the embedding layers, steering the political stance of the summary at inference time. Extensive experiments on three news summarization datasets demonstrate that P$^3$Sum outperforms state-of-the-art summarization systems and large language models by up to 13.7{\%} in terms of the success rate of stance preservation, with competitive performance on standard metrics of summarization quality. Our findings present a first analysis of preservation of pragmatic features in summarization, highlight the lacunae in existing summarization models{---}that even state-of-the-art models often struggle to preserve author{'}s intents{---}and develop new summarization systems that are more faithful to author{'}s perspectives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-p3sum">
<titleInfo>
<title>P³Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangbin</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaochuang</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we take a first step towards designing summarization systems that are faithful to the author’s intent, not only the semantic content of the article. Focusing on a case study of preserving political perspectives in news summarization, we find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the news authors. We thus propose P³Sum, a diffusion model-based summarization approach controlled by political perspective classifiers. In P³Sum, the political leaning of a generated summary is iteratively evaluated at each decoding step, and any drift from the article’s original stance incurs a loss back-propagated to the embedding layers, steering the political stance of the summary at inference time. Extensive experiments on three news summarization datasets demonstrate that P³Sum outperforms state-of-the-art summarization systems and large language models by up to 13.7% in terms of the success rate of stance preservation, with competitive performance on standard metrics of summarization quality. Our findings present a first analysis of preservation of pragmatic features in summarization, highlight the lacunae in existing summarization models—that even state-of-the-art models often struggle to preserve author’s intents—and develop new summarization systems that are more faithful to author’s perspectives.</abstract>
<identifier type="citekey">liu-etal-2024-p3sum</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.119</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.119</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2154</start>
<end>2173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T P³Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models
%A Liu, Yuhan
%A Feng, Shangbin
%A Han, Xiaochuang
%A Balachandran, Vidhisha
%A Park, Chan Young
%A Kumar, Sachin
%A Tsvetkov, Yulia
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F liu-etal-2024-p3sum
%X In this work, we take a first step towards designing summarization systems that are faithful to the author’s intent, not only the semantic content of the article. Focusing on a case study of preserving political perspectives in news summarization, we find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the news authors. We thus propose P³Sum, a diffusion model-based summarization approach controlled by political perspective classifiers. In P³Sum, the political leaning of a generated summary is iteratively evaluated at each decoding step, and any drift from the article’s original stance incurs a loss back-propagated to the embedding layers, steering the political stance of the summary at inference time. Extensive experiments on three news summarization datasets demonstrate that P³Sum outperforms state-of-the-art summarization systems and large language models by up to 13.7% in terms of the success rate of stance preservation, with competitive performance on standard metrics of summarization quality. Our findings present a first analysis of preservation of pragmatic features in summarization, highlight the lacunae in existing summarization models—that even state-of-the-art models often struggle to preserve author’s intents—and develop new summarization systems that are more faithful to author’s perspectives.
%R 10.18653/v1/2024.naacl-long.119
%U https://aclanthology.org/2024.naacl-long.119
%U https://doi.org/10.18653/v1/2024.naacl-long.119
%P 2154-2173
Markdown (Informal)
[P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models](https://aclanthology.org/2024.naacl-long.119) (Liu et al., NAACL 2024)
ACL
- Yuhan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, and Yulia Tsvetkov. 2024. P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2154–2173, Mexico City, Mexico. Association for Computational Linguistics.