Sentence Similarity
Safetensors
roberta
zdanGL commited on
Commit
b7cd708
·
verified ·
1 Parent(s): ccec961

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -113,7 +113,7 @@ for i, definition in enumerate(definitions):
113
  - **Max Sequence Length:** 256 tokens (both mentions and descriptions)
114
 
115
  ### Benchmark Results
116
- - **Dataset:** Zero-Shot Entity Linking [(Logeswaran et al., 2019)](https://arxiv.org/abs/1906.07348) test set. Details in the README [here](https://github.com/lajanugen/zeshel/blob/master/README.md)
117
  - **Metric:** Recall@64
118
  - **Score:** 80.29%
119
  - **Comparison:** [Meta AI's BLINK](https://arxiv.org/pdf/1911.03814) achieves 82.06% on the same test set - slightly higher than ours, however, their model was trained on the training set but ours was not.
 
113
  - **Max Sequence Length:** 256 tokens (both mentions and descriptions)
114
 
115
  ### Benchmark Results
116
+ - **Dataset:** Zero-Shot Entity Linking [(Logeswaran et al., 2019)](https://arxiv.org/abs/1906.07348) test set. More details [here](https://github.com/lajanugen/zeshel/blob/master/README.md)
117
  - **Metric:** Recall@64
118
  - **Score:** 80.29%
119
  - **Comparison:** [Meta AI's BLINK](https://arxiv.org/pdf/1911.03814) achieves 82.06% on the same test set - slightly higher than ours, however, their model was trained on the training set but ours was not.