app.py

import gradio as gr
import model_wrapper


model = model_wrapper.PredictionModel()


def pretty_print_opinion(opinion_dict):
    res = []
    maxlen = max([len(key) for key in opinion_dict.keys()]) + 2
    maxlen = 0
    for key, value in opinion_dict.items():
        if key == 'Polarity':
            res.append(f'{(key + ":").ljust(maxlen)} {value}')
        else:
            res.append(f'{(key + ":").ljust(maxlen)} \'{" ".join(value[0])}\'')
    return '\n'.join(res) + '\n'


def predict(text):
    print(f'Input message "{text}"')
    try:
        predictions = model([text])
        prediction = predictions[0]
        results = []
        if not prediction['opinions']:
            return 'No opinions detected'
        for opinion in prediction['opinions']:
            results.append(pretty_print_opinion(opinion))
        print(f'Successfully predicted SA for input message "{text}": {results}')
        return '\n'.join(results)
    except Exception as e:
        print(f'Error for input message "{text}": {e}')
        raise e



markdown_text = '''
<br>
<br>
This space provides a gradio demo and an easy-to-run wrapper of the pre-trained model for structured sentiment analysis in Norwegian language, pre-trained on the [NoReC dataset](https://huggingface.co/datasets/norec).
This space containt an implementation of method described in "Direct parsing to sentiment graphs" (Samuel _et al._, ACL 2022). The main repository that also contains the scripts for training the model, can be found on the project [github](https://github.com/jerbarnes/direct_parsing_to_sent_graph).

The sentiment graph model is based on an underlying masked language model – [NorBERT 2](https://huggingface.co/ltg/norbert2).
The proposed method suggests three different ways to encode the sentiment graph: "node-centric", "labeled-edge", and "opinion-tuple".
The current model
- uses "labeled-edge" graph encoding
- does not use character-level embedding
- all other hyperparameters are set to [default values](https://github.com/jerbarnes/direct_parsing_to_sent_graph/blob/main/perin/config/edge_norec.yaml)
, and it achieves the following results on the held-out set of the NoReC dataset:

| Unlabeled sentiment tuple F1 | Target F1  | Relative polarity precision |
|:----------------------------:|:----------:|:---------------------------:|
|     0.434                    |  0.541      |        0.926                |


In "Word Substitution with Masked Language Models as Data Augmentation for Sentiment Analysis", we analyzed data augmentation strategies for improving performance of the model. Using masked-language modeling (MLM), we augmented the sentences with MLM-substituted words inside, outside, or inside+outside the actual sentiment tuples. The results below show that augmentation may be improve the model performance. This space, however, runs the original model trained without augmentation.

|                | Augmentation rate | Unlabeled sentiment tuple F1 | Target F1 | Relative polarity precision |
|----------------|-------------------|------------------------------|-----------|-----------------------------|
| Baseline       | 0%               | 43.39                        | 54.13     | 92.59                       |
| Outside        | 59%              | **45.08**                    | 56.18     | 92.95                       |
| Inside         | 9%               | 43.38                        | 55.62     | 92.49                       |
| Inside+Outside | 27%              | 44.12                        | **56.44** | **93.19**               |



The model can be easily used for predicting sentiment tuples as follows: 

```python
>>> import model_wrapper
>>> model = model_wrapper.PredictionModel()
>>> model.predict(['vi liker svart kaffe'])
[{'sent_id': '0',
  'text': 'vi liker svart kaffe',
  'opinions': [{'Source': [['vi'], ['0:2']],
    'Target': [['svart', 'kaffe'], ['9:14', '15:20']],
    'Polar_expression': [['liker'], ['3:8']],
    'Polarity': 'Positive'}]}]
```
'''



with gr.Blocks() as demo:
    with gr.Row() as row:
        text_input = gr.Textbox(label="input")
        text_output = gr.Textbox(label="output")
    with gr.Row() as row:
        text_button = gr.Button("submit")

    text_button.click(fn=predict, inputs=text_input, outputs=text_output)

    gr.Markdown(markdown_text)


demo.launch()