shengz's picture
Change the pipeline tag.
48166e6
|
raw
history blame
2.16 kB
metadata
language: en
tags:
  - exbert
license: mit
pipeline_tag: feature-extraction
widget:
  - text: >-
      We aimed to find drug targets using the 2DE / <ENT> MS </ENT> proteomics
      study of a dexamethasone - resistant cell line.

KRISSBERT

Entity linking faces significant challenges such as prolific variations and prevalent ambiguities, especially in high-value domains with myriad entities. Standard classification approaches suffer from the annotation bottleneck and cannot effectively handle unseen entities. Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia (Logeswaran et al., 2019; Wu et al., 2020). We explore Knowledge-RIch Self-Supervision (KRISS) and train a contextual encoder (KRISSBERT) for entity linking, by leveraging readily available unlabeled text and domain knowledge.

This KRISSBERT is initialized with PubMedBERT parameters, and then trained using self-supervised examples that are generated by combining PubMed abstracts and the UMLS ontology. Experiments on seven standard biomedical entity linking datasets show that KRISSBERT attains new state of the art, outperforming prior self-supervised methods by as much as 20 absolute points in accuracy. See Zhang et al., 2021 for the details.

Citation

If you find KRISSBERT useful in your research, please cite the following paper:

@article{krissbert,
  author = {Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon},
  title = {Knowledge-Rich Self-Supervised Entity Linking},
  year = {2021},
  url = {https://arxiv.org/abs/2112.07887},
  eprinttype = {arXiv},
  eprint = {2112.07887},
}