@inproceedings{wang-shang-2023-towards,
title = "Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative {XML} Path",
author = "Wang, Zilong and
Shang, Jingbo",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.281",
doi = "10.18653/v1/2023.findings-emnlp.281",
pages = "4254--4265",
abstract = "The rapid growth of web pages and the increasing complexity of their structure poses a challenge for web mining models. Web mining models are required to understand semi-structured web pages, particularly when little is known about the subject or template of a new page. Current methods migrate language models to web mining by embedding the XML source code into the transformer or encoding the rendered layout with graph neural networks. However, these approaches do not take into account the relationships between text nodes within and across pages. In this paper, we propose a new approach, ReXMiner, for zero-shot relation extraction in web mining. ReXMiner encodes the shortest relative paths in the Document Object Model (DOM) tree of the web page which is a more accurate and efficient signal for key-value pair extraction within a web page. It also incorporates the popularity of each text node by counting the occurrence of the same text node across different web pages. We use contrastive learning to address the issue of sparsity in relation extraction. Extensive experiments on public benchmarks show that our method, ReXMiner, outperforms the state-of-the-art baselines in the task of zero-shot relation extraction in web mining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-shang-2023-towards">
<titleInfo>
<title>Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</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>Findings of the Association for Computational Linguistics: EMNLP 2023</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>The rapid growth of web pages and the increasing complexity of their structure poses a challenge for web mining models. Web mining models are required to understand semi-structured web pages, particularly when little is known about the subject or template of a new page. Current methods migrate language models to web mining by embedding the XML source code into the transformer or encoding the rendered layout with graph neural networks. However, these approaches do not take into account the relationships between text nodes within and across pages. In this paper, we propose a new approach, ReXMiner, for zero-shot relation extraction in web mining. ReXMiner encodes the shortest relative paths in the Document Object Model (DOM) tree of the web page which is a more accurate and efficient signal for key-value pair extraction within a web page. It also incorporates the popularity of each text node by counting the occurrence of the same text node across different web pages. We use contrastive learning to address the issue of sparsity in relation extraction. Extensive experiments on public benchmarks show that our method, ReXMiner, outperforms the state-of-the-art baselines in the task of zero-shot relation extraction in web mining.</abstract>
<identifier type="citekey">wang-shang-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.281</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.281</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>4254</start>
<end>4265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
%A Wang, Zilong
%A Shang, Jingbo
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wang-shang-2023-towards
%X The rapid growth of web pages and the increasing complexity of their structure poses a challenge for web mining models. Web mining models are required to understand semi-structured web pages, particularly when little is known about the subject or template of a new page. Current methods migrate language models to web mining by embedding the XML source code into the transformer or encoding the rendered layout with graph neural networks. However, these approaches do not take into account the relationships between text nodes within and across pages. In this paper, we propose a new approach, ReXMiner, for zero-shot relation extraction in web mining. ReXMiner encodes the shortest relative paths in the Document Object Model (DOM) tree of the web page which is a more accurate and efficient signal for key-value pair extraction within a web page. It also incorporates the popularity of each text node by counting the occurrence of the same text node across different web pages. We use contrastive learning to address the issue of sparsity in relation extraction. Extensive experiments on public benchmarks show that our method, ReXMiner, outperforms the state-of-the-art baselines in the task of zero-shot relation extraction in web mining.
%R 10.18653/v1/2023.findings-emnlp.281
%U https://aclanthology.org/2023.findings-emnlp.281
%U https://doi.org/10.18653/v1/2023.findings-emnlp.281
%P 4254-4265
Markdown (Informal)
[Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path](https://aclanthology.org/2023.findings-emnlp.281) (Wang & Shang, Findings 2023)
ACL