@inproceedings{zhang-etal-2024-pdf,
title = "{PDF}-to-Tree: Parsing {PDF} Text Blocks into a Tree",
author = "Zhang, Yue and
Zhang, Zhihao and
Lai, Wenbin and
Zhang, Chong and
Gui, Tao and
Zhang, Qi and
Huang, Xuanjing",
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.628",
pages = "10704--10714",
abstract = "In many PDF documents, the reading order of text blocks is missing, which can hinder machine understanding of the document{'}s content.Existing works try to extract one universal reading order for a PDF file.However, applications, like Retrieval Augmented Generation (RAG), require breaking long articles into sections and subsections for better indexing.For this reason, this paper introduces a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure.Since a PDF may contain thousands of text blocks, far exceeding the number of words in a sentence, this paper proposes a transition-based parser that uses a greedy strategy to build the tree structure.Compared to parser for plain text, we also use multi-modal features to encode the parser state.Experiments show that our approach achieves an accuracy of 93.93{\%}, surpassing the performance of baseline methods by an improvement of 6.72{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-pdf">
<titleInfo>
<title>PDF-to-Tree: Parsing PDF Text Blocks into a Tree</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbin</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</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>In many PDF documents, the reading order of text blocks is missing, which can hinder machine understanding of the document’s content.Existing works try to extract one universal reading order for a PDF file.However, applications, like Retrieval Augmented Generation (RAG), require breaking long articles into sections and subsections for better indexing.For this reason, this paper introduces a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure.Since a PDF may contain thousands of text blocks, far exceeding the number of words in a sentence, this paper proposes a transition-based parser that uses a greedy strategy to build the tree structure.Compared to parser for plain text, we also use multi-modal features to encode the parser state.Experiments show that our approach achieves an accuracy of 93.93%, surpassing the performance of baseline methods by an improvement of 6.72%.</abstract>
<identifier type="citekey">zhang-etal-2024-pdf</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.628</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>10704</start>
<end>10714</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PDF-to-Tree: Parsing PDF Text Blocks into a Tree
%A Zhang, Yue
%A Zhang, Zhihao
%A Lai, Wenbin
%A Zhang, Chong
%A Gui, Tao
%A Zhang, Qi
%A Huang, Xuanjing
%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 zhang-etal-2024-pdf
%X In many PDF documents, the reading order of text blocks is missing, which can hinder machine understanding of the document’s content.Existing works try to extract one universal reading order for a PDF file.However, applications, like Retrieval Augmented Generation (RAG), require breaking long articles into sections and subsections for better indexing.For this reason, this paper introduces a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure.Since a PDF may contain thousands of text blocks, far exceeding the number of words in a sentence, this paper proposes a transition-based parser that uses a greedy strategy to build the tree structure.Compared to parser for plain text, we also use multi-modal features to encode the parser state.Experiments show that our approach achieves an accuracy of 93.93%, surpassing the performance of baseline methods by an improvement of 6.72%.
%U https://aclanthology.org/2024.findings-emnlp.628
%P 10704-10714
Markdown (Informal)
[PDF-to-Tree: Parsing PDF Text Blocks into a Tree](https://aclanthology.org/2024.findings-emnlp.628) (Zhang et al., Findings 2024)
ACL
- Yue Zhang, Zhihao Zhang, Wenbin Lai, Chong Zhang, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. PDF-to-Tree: Parsing PDF Text Blocks into a Tree. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10704–10714, Miami, Florida, USA. Association for Computational Linguistics.