Preface:LM-KBC Challenge 2024
Year: 2024
Type: editorial
Abstract: Pretrained language models (LMs) have advanced a range of semantic tasks and have also shown promise for knowledge extraction from the models itself. Although several works have explored this ability in a setting called probing or prompting, the viability of knowledge base construction from LMs remains underexplored. In the 3rd edition of this challenge, participants were asked to build actual disambiguated knowledge bases from LMs, for given subjects and relations. In crucial difference to existing probing benchmarks like LAMA [1], we make no simplifying assumptions on relation cardinalities, i.e., a subject-entity can stand in relation with zero, one, or many object-entities. Furthermore, submissions need to go beyond just ranking predicted surface strings and materialize disambiguated entities in the output, which will be evaluated using established KB metrics of precision and recall. The challenge has a single track for LMs with a parameter level under 10-billion to fit into low computational requirements. The challenge received 8 submissions, of which 5 submitted a paper, and 4 were accepted for presentation. The challenge was collocated with a workshop on related topics, allowing to host extended discussions, related papers, and invited talks.
Source: VU Research Portal
Authors: Kalo, Jan Christoph, Nguyen, Tuan Phong, Razniewski, Simon, Zhang, Bohui
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6995778259