@inproceedings{bouziani-etal-2024-rexel,
title = "{REXEL}: An End-to-end Model for Document-Level Relation Extraction and Entity Linking",
author = "Bouziani, Nacime and
Tyagi, Shubhi and
Fisher, Joseph and
Lehmann, Jens and
Pierleoni, Andrea",
editor = "Yang, Yi and
Davani, Aida and
Sil, Avi and
Kumar, Anoop",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-industry.11",
doi = "10.18653/v1/2024.naacl-industry.11",
pages = "119--130",
abstract = "Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by $\textit{closed information extraction}$ (cIE). However, existing approaches for cIE suffer from two limitations: $\textit{(i)}$ they are often pipelines which makes them prone to error propagation, and/or $\textit{(ii)}$ they are restricted to sentence level which prevents them from capturing long-range dependencies and results in expensive inference time. We address these limitations by proposing REXEL, a highly efficient and accurate model for the joint task of document level cIE (DocIE). REXEL performs mention detection, entity typing, entity disambiguation, coreference resolution and document-level relation classification in a single forward pass to yield facts fully linked to a reference knowledge graph. It is on average 11 times faster than competitive existing approaches in a similar setting and performs competitively both when optimised for any of the individual sub-task and a variety of combinations of different joint tasks, surpassing the baselines by an average of more than 6 F1 points. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale. We also release an extension of the DocRED dataset to enable benchmarking of future work on DocIE, which will be available at https://github.com/amazon-science/e2e-docie.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bouziani-etal-2024-rexel">
<titleInfo>
<title>REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nacime</namePart>
<namePart type="family">Bouziani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubhi</namePart>
<namePart type="family">Tyagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Fisher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens</namePart>
<namePart type="family">Lehmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Pierleoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). However, existing approaches for cIE suffer from two limitations: (i) they are often pipelines which makes them prone to error propagation, and/or (ii) they are restricted to sentence level which prevents them from capturing long-range dependencies and results in expensive inference time. We address these limitations by proposing REXEL, a highly efficient and accurate model for the joint task of document level cIE (DocIE). REXEL performs mention detection, entity typing, entity disambiguation, coreference resolution and document-level relation classification in a single forward pass to yield facts fully linked to a reference knowledge graph. It is on average 11 times faster than competitive existing approaches in a similar setting and performs competitively both when optimised for any of the individual sub-task and a variety of combinations of different joint tasks, surpassing the baselines by an average of more than 6 F1 points. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale. We also release an extension of the DocRED dataset to enable benchmarking of future work on DocIE, which will be available at https://github.com/amazon-science/e2e-docie.</abstract>
<identifier type="citekey">bouziani-etal-2024-rexel</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-industry.11</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-industry.11</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>119</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking
%A Bouziani, Nacime
%A Tyagi, Shubhi
%A Fisher, Joseph
%A Lehmann, Jens
%A Pierleoni, Andrea
%Y Yang, Yi
%Y Davani, Aida
%Y Sil, Avi
%Y Kumar, Anoop
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F bouziani-etal-2024-rexel
%X Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). However, existing approaches for cIE suffer from two limitations: (i) they are often pipelines which makes them prone to error propagation, and/or (ii) they are restricted to sentence level which prevents them from capturing long-range dependencies and results in expensive inference time. We address these limitations by proposing REXEL, a highly efficient and accurate model for the joint task of document level cIE (DocIE). REXEL performs mention detection, entity typing, entity disambiguation, coreference resolution and document-level relation classification in a single forward pass to yield facts fully linked to a reference knowledge graph. It is on average 11 times faster than competitive existing approaches in a similar setting and performs competitively both when optimised for any of the individual sub-task and a variety of combinations of different joint tasks, surpassing the baselines by an average of more than 6 F1 points. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale. We also release an extension of the DocRED dataset to enable benchmarking of future work on DocIE, which will be available at https://github.com/amazon-science/e2e-docie.
%R 10.18653/v1/2024.naacl-industry.11
%U https://aclanthology.org/2024.naacl-industry.11
%U https://doi.org/10.18653/v1/2024.naacl-industry.11
%P 119-130
Markdown (Informal)
[REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking](https://aclanthology.org/2024.naacl-industry.11) (Bouziani et al., NAACL 2024)
ACL
- Nacime Bouziani, Shubhi Tyagi, Joseph Fisher, Jens Lehmann, and Andrea Pierleoni. 2024. REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pages 119–130, Mexico City, Mexico. Association for Computational Linguistics.