Update README.md

README.md

@@ -24,14 +24,8 @@ The FSNER model was proposed in [Example-Based Named Entity Recognition](https:/
 
 ## Installation and Example Usage
 ------
-You need to clone `transformers` repository and go to this directory: `transformers/examples/research_projects/fsner`. Then, you will be able to use the FSNER model in two ways:
-
-1. Install as a package: `python setup.py install` and import the model as shown in the code example below
-
-    or
-
-2. Change directory to `src` and import the model as shown in the code example below
 
+- Installation: `pip install fsner`
 
 
 ```python
@@ -41,8 +35,7 @@ model = FSNERModel("sayef/fsner-bert-base-uncased")
 
 tokenizer = FSNERTokenizerUtils("sayef/fsner-bert-base-uncased")
 
-# size of query and supports must be the same. If you want to find all the entitites in one particular query, just repeat the same query n times where n is equal to the number of supports (or entities).
-
+# size of query and supports must be the same. Each query corresponds to the same index of supports.
 
 query = [
     'KWE 4000 can reach with a maximum speed from up to 450 P/min an accuracy from 50 mg',
@@ -72,7 +65,7 @@ supports = [
 device = 'cpu'
 
 W_query = tokenizer.tokenize(query).to(device)
-W_supports = tokenizer.tokenize([s for support in supports for s in support]).to(device)
+W_supports = tokenizer.tokenize(supports).to(device)
 
 start_prob, end_prob = model(W_query, W_supports)