@inproceedings{tasawong-etal-2024-efficient,
title = "Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning",
author = "Tasawong, Panuthep and
Limkonchotiwat, Peerat and
Manakul, Potsawee and
Udomcharoenchaikit, Can and
Chuangsuwanich, Ekapol and
Nutanong, Sarana",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.855",
pages = "15313--15321",
abstract = "Entity disambiguation (ED) is crucial in natural language processing (NLP) for tasks such as question-answering and information extraction. A major challenge in ED is handling overshadowed entities{---}uncommon entities sharing mention surfaces with common entities. The current approach to enhance performance on these entities involves reasoning over facts in a knowledge base (KB), increasing computational overhead during inference. We argue that the ED performance on overshadowed entities can be enhanced during training by addressing shortcut learning, which does not add computational overhead at inference. We propose a simple yet effective debiasing technique to prevent models from shortcut learning during training. Experiments on a range of ED datasets show that our method achieves state-of-the-art performance without compromising inference speed. Our findings suggest a new research direction for improving entity disambiguation via shortcut learning mitigation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tasawong-etal-2024-efficient">
<titleInfo>
<title>Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Panuthep</namePart>
<namePart type="family">Tasawong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Potsawee</namePart>
<namePart type="family">Manakul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Udomcharoenchaikit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekapol</namePart>
<namePart type="family">Chuangsuwanich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarana</namePart>
<namePart type="family">Nutanong</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>Entity disambiguation (ED) is crucial in natural language processing (NLP) for tasks such as question-answering and information extraction. A major challenge in ED is handling overshadowed entities—uncommon entities sharing mention surfaces with common entities. The current approach to enhance performance on these entities involves reasoning over facts in a knowledge base (KB), increasing computational overhead during inference. We argue that the ED performance on overshadowed entities can be enhanced during training by addressing shortcut learning, which does not add computational overhead at inference. We propose a simple yet effective debiasing technique to prevent models from shortcut learning during training. Experiments on a range of ED datasets show that our method achieves state-of-the-art performance without compromising inference speed. Our findings suggest a new research direction for improving entity disambiguation via shortcut learning mitigation.</abstract>
<identifier type="citekey">tasawong-etal-2024-efficient</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.855</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15313</start>
<end>15321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning
%A Tasawong, Panuthep
%A Limkonchotiwat, Peerat
%A Manakul, Potsawee
%A Udomcharoenchaikit, Can
%A Chuangsuwanich, Ekapol
%A Nutanong, Sarana
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F tasawong-etal-2024-efficient
%X Entity disambiguation (ED) is crucial in natural language processing (NLP) for tasks such as question-answering and information extraction. A major challenge in ED is handling overshadowed entities—uncommon entities sharing mention surfaces with common entities. The current approach to enhance performance on these entities involves reasoning over facts in a knowledge base (KB), increasing computational overhead during inference. We argue that the ED performance on overshadowed entities can be enhanced during training by addressing shortcut learning, which does not add computational overhead at inference. We propose a simple yet effective debiasing technique to prevent models from shortcut learning during training. Experiments on a range of ED datasets show that our method achieves state-of-the-art performance without compromising inference speed. Our findings suggest a new research direction for improving entity disambiguation via shortcut learning mitigation.
%U https://aclanthology.org/2024.emnlp-main.855
%P 15313-15321
Markdown (Informal)
[Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning](https://aclanthology.org/2024.emnlp-main.855) (Tasawong et al., EMNLP 2024)
ACL
- Panuthep Tasawong, Peerat Limkonchotiwat, Potsawee Manakul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, and Sarana Nutanong. 2024. Efficient Overshadowed Entity Disambiguation by Mitigating Shortcut Learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15313–15321, Miami, Florida, USA. Association for Computational Linguistics.