shengz commited on
Commit
aa13fed
1 Parent(s): 9b2b2bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -8,7 +8,8 @@ widget:
8
  - text: "<ENT> ER </ENT> crowding has become a wide-spread problem."
9
  ---
10
 
11
- ## KRISSBERT
 
12
 
13
  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](https://aclanthology.org/P19-1335.pdf); [Wu et al., 2020](https://aclanthology.org/2020.emnlp-main.519.pdf)). 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.
14
 
@@ -68,5 +69,4 @@ If you find KRISSBERT useful in your research, please cite the following paper:
68
  eprinttype = {arXiv},
69
  eprint = {2112.07887},
70
  }
71
- ```
72
- [https://arxiv.org/pdf/2112.07887.pdf](https://arxiv.org/pdf/2112.07887.pdf)
 
8
  - text: "<ENT> ER </ENT> crowding has become a wide-spread problem."
9
  ---
10
 
11
+ ## KRISSBERT
12
+ [https://arxiv.org/pdf/2112.07887.pdf](https://arxiv.org/pdf/2112.07887.pdf)
13
 
14
  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](https://aclanthology.org/P19-1335.pdf); [Wu et al., 2020](https://aclanthology.org/2020.emnlp-main.519.pdf)). 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.
15
 
 
69
  eprinttype = {arXiv},
70
  eprint = {2112.07887},
71
  }
72
+ ```