@inproceedings{deshmukh-etal-2025-entities,
title = "All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing",
author = "Deshmukh, Advait and
Umadi, Ashwin and
Srinivas, Dananjay and
Pacheco, Maria Leonor",
editor = "Frermann, Lea and
Stevenson, Mark",
booktitle = "Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.starsem-1.15/",
pages = "189--201",
ISBN = "979-8-89176-340-1",
abstract = "Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity typing tasks where the space of labels is extremely large. In this work, we explore the limitations of the knowledge acquired by PLMs by proposing a novel heuristic to approximate the pre-training distribution of entities when the pre-training data is unknown. Then, we systematically demonstrate that entity-typing approaches that rely solely on the parametric knowledge of PLMs struggle significantly with entities at the long tail of the pre-training distribution, and that knowledge-infused approaches can account for some of these shortcomings. Our findings suggest that we need to go beyond PLMs to produce solutions that perform well for infrequent entities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deshmukh-etal-2025-entities">
<titleInfo>
<title>All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Advait</namePart>
<namePart type="family">Deshmukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwin</namePart>
<namePart type="family">Umadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dananjay</namePart>
<namePart type="family">Srinivas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Stevenson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-340-1</identifier>
</relatedItem>
<abstract>Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity typing tasks where the space of labels is extremely large. In this work, we explore the limitations of the knowledge acquired by PLMs by proposing a novel heuristic to approximate the pre-training distribution of entities when the pre-training data is unknown. Then, we systematically demonstrate that entity-typing approaches that rely solely on the parametric knowledge of PLMs struggle significantly with entities at the long tail of the pre-training distribution, and that knowledge-infused approaches can account for some of these shortcomings. Our findings suggest that we need to go beyond PLMs to produce solutions that perform well for infrequent entities.</abstract>
<identifier type="citekey">deshmukh-etal-2025-entities</identifier>
<location>
<url>https://aclanthology.org/2025.starsem-1.15/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>189</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
%A Deshmukh, Advait
%A Umadi, Ashwin
%A Srinivas, Dananjay
%A Pacheco, Maria Leonor
%Y Frermann, Lea
%Y Stevenson, Mark
%S Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-340-1
%F deshmukh-etal-2025-entities
%X Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity typing tasks where the space of labels is extremely large. In this work, we explore the limitations of the knowledge acquired by PLMs by proposing a novel heuristic to approximate the pre-training distribution of entities when the pre-training data is unknown. Then, we systematically demonstrate that entity-typing approaches that rely solely on the parametric knowledge of PLMs struggle significantly with entities at the long tail of the pre-training distribution, and that knowledge-infused approaches can account for some of these shortcomings. Our findings suggest that we need to go beyond PLMs to produce solutions that perform well for infrequent entities.
%U https://aclanthology.org/2025.starsem-1.15/
%P 189-201
Markdown (Informal)
[All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing](https://aclanthology.org/2025.starsem-1.15/) (Deshmukh et al., *SEM 2025)
ACL