Problem of using Transformers pipeline for sentiment analysis

Rasa Open Source
1

Hi, rasa community, I followed this post for realizing sentiment analysis. I want to use a pre-trained sentiment analysis model. But instead of using NLTK Vader, I used Transformers pipeline. When testing NLU, it works fine, but when testing the entire chatbot, it will throw a asyncio error.

After typing “hi”:

Bot loaded. Type a message and press enter (use '/stop' to exit):
Your input ->  hi
Some layers from the model checkpoint at distilbert-base-uncased-finetuned-sst-2-english were not used when initializing TFDistilBertForSequenceClassification: ['dropout_19']
- This IS expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing TFDistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).

After a while, throw error:

2022-04-08 10:53:09 ERROR    asyncio  - Task exception was never retrieved
future: <Task finished name='Task-2' coro=<configure_app.<locals>.run_cmdline_io() done, defined at /Users/baoyue/miniconda3/envs/rasa3/lib/python3.8/site-packages/rasa/core/run.py:131> exception=TimeoutError()>

Here’s my code:

class SentimentAnalyzer(Component):
    """A pre-trained sentiment component"""

    name = "sentiment"
    provides = ["entities"]
    requires = []
    defaults = {}
    language_list = ["en"]

    def __init__(self, component_config=None):
        super(SentimentAnalyzer, self).__init__(component_config)

    def train(self, training_data, cfg, **kwargs):
        """Not needed, because the the model is pretrained"""
        pass



    def convert_to_rasa(self, value, confidence):
        """Convert model output into the Rasa NLU compatible output format."""
        
        entity = {"value": value,
                  "confidence": confidence,
                  "entity": "sentiment",
                  "extractor": "sentiment_extractor"}

        return entity


    def process(self, message, **kwargs):
        """Retrieve the text message, pass it to the classifier
            and append the prediction results to the message class."""
  
        classifier = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
        res = classifier(str(message.get("text")))
        key, value = res[0]['label'], res[0]['score']

        entity = self.convert_to_rasa(key, value)

        message.set("entities", [entity], add_to_output=True)

    def persist(self, file_name, model_dir):
        """Pass because a pre-trained model is already persisted"""
        pass

Hope to hear from you soon. Thanks!