Delete usage/README.md
Browse files- usage/README.md +0 -43
usage/README.md
DELETED
@@ -1,43 +0,0 @@
|
|
1 |
-
# Knowledge-Rich Self-Supervision (KRISS) for Biomedical Entity Linking
|
2 |
-
|
3 |
-
Usage code for the entity linking approach described in the following paper:
|
4 |
-
```bibtex
|
5 |
-
@article{kriss,
|
6 |
-
author = {Sheng Zhang, Hao Cheng, Shikhar Vashishth, Cliff Wong, Jinfeng Xiao, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, Hoifung Poon},
|
7 |
-
title = {Knowledge-Rich Self-Supervision for Biomedical Entity Linking},
|
8 |
-
year = {2021},
|
9 |
-
url = {https://arxiv.org/abs/2112.07887},
|
10 |
-
eprinttype = {arXiv},
|
11 |
-
eprint = {2112.07887},
|
12 |
-
}
|
13 |
-
```
|
14 |
-
[https://arxiv.org/pdf/2112.07887.pdf](https://arxiv.org/pdf/2112.07887.pdf)
|
15 |
-
|
16 |
-
## Usage of KRISS for Entity Linking
|
17 |
-
|
18 |
-
Here, we use the [MedMentions](https://github.com/chanzuckerberg/MedMentions) data to show you how to 1) generate prototype embeddings, and 2) run entity linking.
|
19 |
-
|
20 |
-
(We are currently unable to release the self-supervised mention examples, because they requires UMLS and PubMed licenses.)
|
21 |
-
|
22 |
-
|
23 |
-
### 1. Create conda environment and install requirements
|
24 |
-
```bash
|
25 |
-
conda create -n kriss -y python=3.8 && conda activate kriss
|
26 |
-
pip install -r requirements.txt
|
27 |
-
```
|
28 |
-
|
29 |
-
### 2. Download the MedMentions dataset
|
30 |
-
|
31 |
-
```bash
|
32 |
-
git clone https://github.com/chanzuckerberg/MedMentions.git
|
33 |
-
```
|
34 |
-
|
35 |
-
### 3. Generate prototype embeddings
|
36 |
-
```bash
|
37 |
-
python generate_prototypes.py
|
38 |
-
```
|
39 |
-
|
40 |
-
### 4. Run entity linking
|
41 |
-
```bash
|
42 |
-
python run_entity_linking.py
|
43 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|