DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph

Publikation: Andere wissenschaftliche BeiträgeAndereForschung

Standard

Harvard

APA

Vancouver

Bibtex

@misc{10c24c78acbb499ca81b27dfc2f04b7b,
title = "DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph",
abstract = " In this work we present an entity linker for DBLP's 2025 version of RDF-based Knowledge Graph. Compared to the 2022 version, DBLP now considers publication venues as a new entity type called dblp:Stream. In the earlier version of DBLPLink, we trained KG-embeddings and re-rankers on a dataset to produce entity linkings. In contrast, in this work, we develop a zero-shot entity linker using LLMs using a novel method, where we re-rank candidate entities based on the log-probabilities of the {"}yes{"} token output at the penultimate layer of the LLM. ",
keywords = "cs.CL",
author = "Debayan Banerjee and Taffa, {Tilahun Abedissa} and Ricardo Usbeck",
year = "2025",
month = jul,
day = "30",
language = "Undefined/Unknown",
type = "Other",

}

RIS

TY - GEN

T1 - DBLPLink 2.0 -- An Entity Linker for the DBLP Scholarly Knowledge Graph

AU - Banerjee, Debayan

AU - Taffa, Tilahun Abedissa

AU - Usbeck, Ricardo

PY - 2025/7/30

Y1 - 2025/7/30

N2 - In this work we present an entity linker for DBLP's 2025 version of RDF-based Knowledge Graph. Compared to the 2022 version, DBLP now considers publication venues as a new entity type called dblp:Stream. In the earlier version of DBLPLink, we trained KG-embeddings and re-rankers on a dataset to produce entity linkings. In contrast, in this work, we develop a zero-shot entity linker using LLMs using a novel method, where we re-rank candidate entities based on the log-probabilities of the "yes" token output at the penultimate layer of the LLM.

AB - In this work we present an entity linker for DBLP's 2025 version of RDF-based Knowledge Graph. Compared to the 2022 version, DBLP now considers publication venues as a new entity type called dblp:Stream. In the earlier version of DBLPLink, we trained KG-embeddings and re-rankers on a dataset to produce entity linkings. In contrast, in this work, we develop a zero-shot entity linker using LLMs using a novel method, where we re-rank candidate entities based on the log-probabilities of the "yes" token output at the penultimate layer of the LLM.

KW - cs.CL

M3 - Other

ER -

Dokumente

  • 2507.22811v1

    685 KB, PDF-Dokument