sayef
/

fsner-bert-base-uncased

@@ -2,27 +2,23 @@
 Implemented by [sayef](https://huggingface.co/sayef).
-## Overview
-The FSNER model was proposed in [Example-Based Named Entity Recognition](https://arxiv.org/abs/2008.10570) by Morteza Ziyadi, Yuting Sun, Abhishek Goswami, Jade Huang, Weizhu Chen. To identify entity spans in a new domain, it uses a train-free few-shot learning approach inspired by question-answering.
 ## Abstract
-----
-> We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. Our train-free few-shot learning approach takes inspiration from question-answering to identify entity spans in a new and unseen domain. In comparison with the current state-of-the-art, the proposed method performs significantly better, especially when using a low number of support examples.
 ## Model Training Details
------
 | identifier        | epochs |                                            datasets                                             |
 | ---------- |:------:|:-----------------------------------------------------------------------------------------------:|
 | [sayef/fsner-bert-base-uncased](https://huggingface.co/sayef/fsner-bert-base-uncased)      |   25   |  ontonotes5, conll2003, wnut2017, mit_movie_trivia, mit_restaurant and fin (Alvarado et al.).   |
 ## Installation and Example Usage
-------
 You can use the FSNER model in 3 ways:
@@ -30,18 +26,18 @@ You can use the FSNER model in 3 ways:
    or
-2. Install from source: `python setup.py install` and import the model as shown in the code example below
    or
-3. Clone [repo](https://github.com/sayef/fsner) and add absolute path of `fsner/src` directory to your PYTHONPATH and import the model as shown in the code example below
 ```python
 import json
 from fsner import FSNERModel, FSNERTokenizerUtils, pretty_embed
 query_texts = [
     "Does Luke's serve lunch?",
     "Chang does not speak Taiwanese very well.",
@@ -73,7 +69,6 @@ support_texts = {
 device = 'cpu'
 tokenizer = FSNERTokenizerUtils("sayef/fsner-bert-base-uncased")
 queries = tokenizer.tokenize(query_texts).to(device)
 supports = tokenizer.tokenize(list(support_texts.values())).to(device)
@@ -94,11 +89,10 @@ output = tokenizer.extract_entity_from_scores(query_texts, queries, p_starts, p_
 print(json.dumps(output, indent=2))
-# install spacy for pretty embed
 pretty_embed(query_texts, output, list(support_texts.keys()))
 ```
 <!DOCTYPE html>
 <html lang="en">
     <head>
@@ -126,10 +120,12 @@ pretty_embed(query_texts, output, list(support_texts.keys()))
 </body>
 </html>
 ## Datasets preparation
 1. We need to convert dataset into the following format. Let's say we have a dataset file train.json like following.
 ```json
 {
@@ -158,10 +154,10 @@ pretty_embed(query_texts, output, list(support_texts.keys()))
     1. [train](https://gist.githubusercontent.com/sayef/46deaf7e6c6e1410b430ddc8aff9c557/raw/ea7ae2ae933bfc9c0daac1aa52a9dc093d5b36f4/ontonotes5.train.json)
     2. [dev](https://gist.githubusercontent.com/sayef/46deaf7e6c6e1410b430ddc8aff9c557/raw/ea7ae2ae933bfc9c0daac1aa52a9dc093d5b36f4/ontonotes5.dev.json)
-3. Then one could use examples/train.py script to train/evaluate your fsner model.
 ```bash
-python train.py --pretrained-model bert-base-uncased --mode train --train-data train.json --val-data val.json \
                 --train-batch-size 6 --val-batch-size 6 --n-examples-per-entity 10 --neg-example-batch-ratio 1/3 --max-epochs 25 --device gpu \
                 --gpus -1 --strategy ddp
 ```

 Implemented by [sayef](https://huggingface.co/sayef).
+# Overview
+The FSNER model was proposed in [Example-Based Named Entity Recognition](https://arxiv.org/abs/2008.10570) by Morteza
+Ziyadi, Yuting Sun, Abhishek Goswami, Jade Huang, Weizhu Chen. To identify entity spans in a new domain, it uses a
+train-free few-shot learning approach inspired by question-answering.
 ## Abstract
+> We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. Our train-free few-shot learning approach takes inspiration from question-answering to identify entity spans in a new and unseen domain. In comparison with the current state-of-the-art, the proposed method performs significantly better, especially when using a low number of support examples.
 ## Model Training Details
 | identifier        | epochs |                                            datasets                                             |
 | ---------- |:------:|:-----------------------------------------------------------------------------------------------:|
 | [sayef/fsner-bert-base-uncased](https://huggingface.co/sayef/fsner-bert-base-uncased)      |   25   |  ontonotes5, conll2003, wnut2017, mit_movie_trivia, mit_restaurant and fin (Alvarado et al.).   |
 ## Installation and Example Usage
 You can use the FSNER model in 3 ways:
    or
+2. Install from source: `python install .` and import the model as shown in the code example below
    or
+3. Clone [repo](https://github.com/sayef/fsner) and add absolute path of `fsner/src` directory to your PYTHONPATH and
+   import the model as shown in the code example below
 ```python
 import json
 from fsner import FSNERModel, FSNERTokenizerUtils, pretty_embed
 query_texts = [
     "Does Luke's serve lunch?",
     "Chang does not speak Taiwanese very well.",
 device = 'cpu'
 tokenizer = FSNERTokenizerUtils("sayef/fsner-bert-base-uncased")
 queries = tokenizer.tokenize(query_texts).to(device)
 supports = tokenizer.tokenize(list(support_texts.values())).to(device)
 print(json.dumps(output, indent=2))
+# install displacy for pretty embed
 pretty_embed(query_texts, output, list(support_texts.keys()))
 ```
 <!DOCTYPE html>
 <html lang="en">
     <head>
 </body>
 </html>
 ## Datasets preparation
 1. We need to convert dataset into the following format. Let's say we have a dataset file train.json like following.
+2. Each list in supports are the examples of one entity type
+3. Wrap entities around with [E] and [/E] in the examples.
+4. Each example should have only one pair of [E] ... [/E].
 ```json
 {
     1. [train](https://gist.githubusercontent.com/sayef/46deaf7e6c6e1410b430ddc8aff9c557/raw/ea7ae2ae933bfc9c0daac1aa52a9dc093d5b36f4/ontonotes5.train.json)
     2. [dev](https://gist.githubusercontent.com/sayef/46deaf7e6c6e1410b430ddc8aff9c557/raw/ea7ae2ae933bfc9c0daac1aa52a9dc093d5b36f4/ontonotes5.dev.json)
+3. Then trainer script can be used to train/evaluate your fsner model.
 ```bash
+fsner trainer --pretrained-model bert-base-uncased --mode train --train-data train.json --val-data val.json \
                 --train-batch-size 6 --val-batch-size 6 --n-examples-per-entity 10 --neg-example-batch-ratio 1/3 --max-epochs 25 --device gpu \
                 --gpus -1 --strategy ddp
 ```