@inproceedings{liu-etal-2023-webdp,
title = "{W}eb{DP}: Understanding Discourse Structures in Semi-Structured Web Documents",
author = "Liu, Peilin and
Lin, Hongyu and
Liao, Meng and
Xiang, Hao and
Han, Xianpei and
Sun, Le",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.650",
doi = "10.18653/v1/2023.findings-acl.650",
pages = "10235--10258",
abstract = "Web documents have become rich data resources in current era, and understanding their discourse structure will potentially benefit various downstream document processing applications. Unfortunately, current discourse analysis and document intelligence research mostly focus on either discourse structure of plain text or superficial visual structures in document, which cannot accurately describe discourse structure of highly free-styled and semi-structured web documents. To promote discourse studies on web documents, in this paper we introduced a benchmark {--} WebDP, orienting a new task named Web Document Discourse Parsing. Specifically, a web document discourse structure representation schema is proposed by extending classical discourse theories and adding special features to well represent discourse characteristics of web documents. Then, a manually annotated web document dataset {--} WEBDOCS is developed to facilitate the study of this parsing task. We compared current neural models on WEBDOCS and experimental results show that WebDP is feasible but also challenging for current models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-webdp">
<titleInfo>
<title>WebDP: Understanding Discourse Structures in Semi-Structured Web Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peilin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Web documents have become rich data resources in current era, and understanding their discourse structure will potentially benefit various downstream document processing applications. Unfortunately, current discourse analysis and document intelligence research mostly focus on either discourse structure of plain text or superficial visual structures in document, which cannot accurately describe discourse structure of highly free-styled and semi-structured web documents. To promote discourse studies on web documents, in this paper we introduced a benchmark – WebDP, orienting a new task named Web Document Discourse Parsing. Specifically, a web document discourse structure representation schema is proposed by extending classical discourse theories and adding special features to well represent discourse characteristics of web documents. Then, a manually annotated web document dataset – WEBDOCS is developed to facilitate the study of this parsing task. We compared current neural models on WEBDOCS and experimental results show that WebDP is feasible but also challenging for current models.</abstract>
<identifier type="citekey">liu-etal-2023-webdp</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.650</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.650</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10235</start>
<end>10258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WebDP: Understanding Discourse Structures in Semi-Structured Web Documents
%A Liu, Peilin
%A Lin, Hongyu
%A Liao, Meng
%A Xiang, Hao
%A Han, Xianpei
%A Sun, Le
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-webdp
%X Web documents have become rich data resources in current era, and understanding their discourse structure will potentially benefit various downstream document processing applications. Unfortunately, current discourse analysis and document intelligence research mostly focus on either discourse structure of plain text or superficial visual structures in document, which cannot accurately describe discourse structure of highly free-styled and semi-structured web documents. To promote discourse studies on web documents, in this paper we introduced a benchmark – WebDP, orienting a new task named Web Document Discourse Parsing. Specifically, a web document discourse structure representation schema is proposed by extending classical discourse theories and adding special features to well represent discourse characteristics of web documents. Then, a manually annotated web document dataset – WEBDOCS is developed to facilitate the study of this parsing task. We compared current neural models on WEBDOCS and experimental results show that WebDP is feasible but also challenging for current models.
%R 10.18653/v1/2023.findings-acl.650
%U https://aclanthology.org/2023.findings-acl.650
%U https://doi.org/10.18653/v1/2023.findings-acl.650
%P 10235-10258
Markdown (Informal)
[WebDP: Understanding Discourse Structures in Semi-Structured Web Documents](https://aclanthology.org/2023.findings-acl.650) (Liu et al., Findings 2023)
ACL