@inproceedings{atri-etal-2023-promoting,
title = "Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph",
author = "Atri, Yash Kumar and
Iyer, Arun and
Chakraborty, Tanmoy and
Goyal, Vikram",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.133",
doi = "10.18653/v1/2023.emnlp-main.133",
pages = "2154--2166",
abstract = "Multi-document Summarization (MDS) characterizes compressing information from multiple source documents to its succinct summary. An ideal summary should encompass all topics and accurately model cross-document relations expounded upon in the source documents. However, existing systems either impose constraints on the length of tokens during the encoding or falter in capturing the intricate cross-document relationships. These limitations impel the systems to produce summaries that are non-factual and unfaithful, thereby imparting an unfair comprehension of the topic to the readers. To counter these limitations and promote the information equivalence between the source document and generated summary, we propose FIBER, a novel encoder-decoder model that uses pre-trained BART to comprehensively analyze linguistic nuances, simplicial complex layer to apprehend inherent properties that transcend pairwise associations and sheaf graph attention to effectively capture the heterophilic properties. We benchmark FIBER with eleven baselines over four widely-used MDS datasets {--} Multinews, CQASumm, DUC and Opinosis, and show that FIBER achieves consistent performance improvement across all the evaluation metrics (syntactical, semantical and faithfulness). We corroborate these improvements further through qualitative human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atri-etal-2023-promoting">
<titleInfo>
<title>Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Atri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vikram</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-document Summarization (MDS) characterizes compressing information from multiple source documents to its succinct summary. An ideal summary should encompass all topics and accurately model cross-document relations expounded upon in the source documents. However, existing systems either impose constraints on the length of tokens during the encoding or falter in capturing the intricate cross-document relationships. These limitations impel the systems to produce summaries that are non-factual and unfaithful, thereby imparting an unfair comprehension of the topic to the readers. To counter these limitations and promote the information equivalence between the source document and generated summary, we propose FIBER, a novel encoder-decoder model that uses pre-trained BART to comprehensively analyze linguistic nuances, simplicial complex layer to apprehend inherent properties that transcend pairwise associations and sheaf graph attention to effectively capture the heterophilic properties. We benchmark FIBER with eleven baselines over four widely-used MDS datasets – Multinews, CQASumm, DUC and Opinosis, and show that FIBER achieves consistent performance improvement across all the evaluation metrics (syntactical, semantical and faithfulness). We corroborate these improvements further through qualitative human evaluation.</abstract>
<identifier type="citekey">atri-etal-2023-promoting</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.133</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.133</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>2154</start>
<end>2166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph
%A Atri, Yash Kumar
%A Iyer, Arun
%A Chakraborty, Tanmoy
%A Goyal, Vikram
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F atri-etal-2023-promoting
%X Multi-document Summarization (MDS) characterizes compressing information from multiple source documents to its succinct summary. An ideal summary should encompass all topics and accurately model cross-document relations expounded upon in the source documents. However, existing systems either impose constraints on the length of tokens during the encoding or falter in capturing the intricate cross-document relationships. These limitations impel the systems to produce summaries that are non-factual and unfaithful, thereby imparting an unfair comprehension of the topic to the readers. To counter these limitations and promote the information equivalence between the source document and generated summary, we propose FIBER, a novel encoder-decoder model that uses pre-trained BART to comprehensively analyze linguistic nuances, simplicial complex layer to apprehend inherent properties that transcend pairwise associations and sheaf graph attention to effectively capture the heterophilic properties. We benchmark FIBER with eleven baselines over four widely-used MDS datasets – Multinews, CQASumm, DUC and Opinosis, and show that FIBER achieves consistent performance improvement across all the evaluation metrics (syntactical, semantical and faithfulness). We corroborate these improvements further through qualitative human evaluation.
%R 10.18653/v1/2023.emnlp-main.133
%U https://aclanthology.org/2023.emnlp-main.133
%U https://doi.org/10.18653/v1/2023.emnlp-main.133
%P 2154-2166
Markdown (Informal)
[Promoting Topic Coherence and Inter-Document Consorts in Multi-Document Summarization via Simplicial Complex and Sheaf Graph](https://aclanthology.org/2023.emnlp-main.133) (Atri et al., EMNLP 2023)
ACL