@inproceedings{singha-roy-etal-2024-graph,
title = "Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification",
author = "Singha Roy, Sudipta and
Wang, Xindi and
Mercer, Robert and
Rudzicz, Frank",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.257/",
doi = "10.18653/v1/2024.findings-emnlp.257",
pages = "4460--4470",
abstract = "Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. To address these constraints, we propose a novel model leveraging a graph-tree structure. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts, respectively. We use Tree Transformers to generate sentence encodings, while a graph attention network models inter- and intra-sentence dependencies. During training, we implement bidirectional information propagation from word-to-sentence-to-document and vice versa, which enriches the contextual representation. Our proposed method enables a comprehensive understanding of content at all hierarchical levels and effectively handles arbitrarily long contexts without token limit constraints. Experimental results demonstrate the effectiveness of our approach in all types of long document classification tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singha-roy-etal-2024-graph">
<titleInfo>
<title>Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Singha Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xindi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Mercer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Rudzicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. To address these constraints, we propose a novel model leveraging a graph-tree structure. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts, respectively. We use Tree Transformers to generate sentence encodings, while a graph attention network models inter- and intra-sentence dependencies. During training, we implement bidirectional information propagation from word-to-sentence-to-document and vice versa, which enriches the contextual representation. Our proposed method enables a comprehensive understanding of content at all hierarchical levels and effectively handles arbitrarily long contexts without token limit constraints. Experimental results demonstrate the effectiveness of our approach in all types of long document classification tasks.</abstract>
<identifier type="citekey">singha-roy-etal-2024-graph</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.257</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.257/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>4460</start>
<end>4470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification
%A Singha Roy, Sudipta
%A Wang, Xindi
%A Mercer, Robert
%A Rudzicz, Frank
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F singha-roy-etal-2024-graph
%X Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model hierarchical relationships within documents. To address these constraints, we propose a novel model leveraging a graph-tree structure. Our approach integrates syntax trees for sentence encodings and document graphs for document encodings, which capture fine-grained syntactic relationships and broader document contexts, respectively. We use Tree Transformers to generate sentence encodings, while a graph attention network models inter- and intra-sentence dependencies. During training, we implement bidirectional information propagation from word-to-sentence-to-document and vice versa, which enriches the contextual representation. Our proposed method enables a comprehensive understanding of content at all hierarchical levels and effectively handles arbitrarily long contexts without token limit constraints. Experimental results demonstrate the effectiveness of our approach in all types of long document classification tasks.
%R 10.18653/v1/2024.findings-emnlp.257
%U https://aclanthology.org/2024.findings-emnlp.257/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.257
%P 4460-4470
Markdown (Informal)
[Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification](https://aclanthology.org/2024.findings-emnlp.257/) (Singha Roy et al., Findings 2024)
ACL