English

UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models

Computation and Language 2023-05-08 v2

Abstract

Recent research demonstrates that external knowledge injection can advance pre-trained language models (PLMs) in a variety of downstream NLP tasks. However, existing knowledge injection methods are either applicable to structured knowledge or unstructured knowledge, lacking a unified usage. In this paper, we propose a UNified knowledge inTERface, UNTER, to provide a unified perspective to exploit both structured knowledge and unstructured knowledge. In UNTER, we adopt the decoder as a unified knowledge interface, aligning span representations obtained from the encoder with their corresponding knowledge. This approach enables the encoder to uniformly invoke span-related knowledge from its parameters for downstream applications. Experimental results show that, with both forms of knowledge injected, UNTER gains continuous improvements on a series of knowledge-driven NLP tasks, including entity typing, named entity recognition and relation extraction, especially in low-resource scenarios.

Keywords

Cite

@article{arxiv.2305.01624,
  title  = {UNTER: A Unified Knowledge Interface for Enhancing Pre-trained Language Models},
  author = {Deming Ye and Yankai Lin and Zhengyan Zhang and Maosong Sun},
  journal= {arXiv preprint arXiv:2305.01624},
  year   = {2023}
}

Comments

8 pages

R2 v1 2026-06-28T10:23:44.536Z