All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2410.17355 (cs)
[Submitted on 22 Oct 2024 (v1), last revised 11 Sep 2026 (this version, v4)]
Title:All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
View a PDF of the paper titled All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing, by Advait Deshmukh and 3 other authors
View PDF
HTML (experimental)
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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2410.17355 [cs.CL] |
| (or arXiv:2410.17355v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2410.17355
arXiv-issued DOI via DataCite
|
|
| Journal reference: | StarSEM 2025 |
| Related DOI: | https://doi.org/10.18653/v1/2025.starsem-1.15
DOI(s) linking to related resources
|
Submission history
From: Dananjay Srinivas [view email][v1] Tue, 22 Oct 2024 18:47:46 UTC (683 KB)
[v2] Fri, 27 Jun 2025 14:47:42 UTC (986 KB)
[v3] Mon, 10 Nov 2025 14:01:06 UTC (628 KB)
[v4] Fri, 11 Sep 2026 15:48:47 UTC (621 KB)
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing, by Advait Deshmukh and 3 other authors
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.