@inproceedings{wang-zhang-2024-pre,
title = "Pre-trained Language Models for Entity Blocking: A Reproducibility Study",
author = "Wang, Runhui and
Zhang, Yongfeng",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.483",
doi = "10.18653/v1/2024.naacl-long.483",
pages = "8720--8730",
abstract = "Entity Resolution (ER) is an essential task in data integration and its goal is to find records that represent the same entity in a dataset. Deep learning models, especially large pre-trained language models, have achieved state-of-the-art results on this task. A typical ER pipeline consists of Entity Blocking and Entity Matching: Entity Blocking finds candidate record pairs that potentially match and Entity Matching determines if the pairs match. The goal of the entity blocking step is to include as many matching pairs as possible while including as few non-matching pairs as possible. On the other hand, the blocking task can also be considered as an Information Retrieval (IR) task. However, state-of-the-art neural IR models that are based on large language models have not been evaluated on the ER task. What{'}s more, the generalization ability of state-of-the-art methods for entity blocking is not well-studied but an import aspect in real-world applications. In this work, we evaluate state-of-the-art models for Entity Blocking along with neural IR models on a wide range of real-world datasets, and also study their in-distribution and out-of-distribution generalization abilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-zhang-2024-pre">
<titleInfo>
<title>Pre-trained Language Models for Entity Blocking: A Reproducibility Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Runhui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongfeng</namePart>
<namePart type="family">Zhang</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 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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>Entity Resolution (ER) is an essential task in data integration and its goal is to find records that represent the same entity in a dataset. Deep learning models, especially large pre-trained language models, have achieved state-of-the-art results on this task. A typical ER pipeline consists of Entity Blocking and Entity Matching: Entity Blocking finds candidate record pairs that potentially match and Entity Matching determines if the pairs match. The goal of the entity blocking step is to include as many matching pairs as possible while including as few non-matching pairs as possible. On the other hand, the blocking task can also be considered as an Information Retrieval (IR) task. However, state-of-the-art neural IR models that are based on large language models have not been evaluated on the ER task. What’s more, the generalization ability of state-of-the-art methods for entity blocking is not well-studied but an import aspect in real-world applications. In this work, we evaluate state-of-the-art models for Entity Blocking along with neural IR models on a wide range of real-world datasets, and also study their in-distribution and out-of-distribution generalization abilities.</abstract>
<identifier type="citekey">wang-zhang-2024-pre</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.483</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.483</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>8720</start>
<end>8730</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-trained Language Models for Entity Blocking: A Reproducibility Study
%A Wang, Runhui
%A Zhang, Yongfeng
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-zhang-2024-pre
%X Entity Resolution (ER) is an essential task in data integration and its goal is to find records that represent the same entity in a dataset. Deep learning models, especially large pre-trained language models, have achieved state-of-the-art results on this task. A typical ER pipeline consists of Entity Blocking and Entity Matching: Entity Blocking finds candidate record pairs that potentially match and Entity Matching determines if the pairs match. The goal of the entity blocking step is to include as many matching pairs as possible while including as few non-matching pairs as possible. On the other hand, the blocking task can also be considered as an Information Retrieval (IR) task. However, state-of-the-art neural IR models that are based on large language models have not been evaluated on the ER task. What’s more, the generalization ability of state-of-the-art methods for entity blocking is not well-studied but an import aspect in real-world applications. In this work, we evaluate state-of-the-art models for Entity Blocking along with neural IR models on a wide range of real-world datasets, and also study their in-distribution and out-of-distribution generalization abilities.
%R 10.18653/v1/2024.naacl-long.483
%U https://aclanthology.org/2024.naacl-long.483
%U https://doi.org/10.18653/v1/2024.naacl-long.483
%P 8720-8730
Markdown (Informal)
[Pre-trained Language Models for Entity Blocking: A Reproducibility Study](https://aclanthology.org/2024.naacl-long.483) (Wang & Zhang, NAACL 2024)
ACL
- Runhui Wang and Yongfeng Zhang. 2024. Pre-trained Language Models for Entity Blocking: A Reproducibility Study. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8720–8730, Mexico City, Mexico. Association for Computational Linguistics.