Integrating POS Tagging with the turian/flair-pos-english Cognitive Actions

22 Apr 2025
Integrating POS Tagging with the turian/flair-pos-english Cognitive Actions

In the world of Natural Language Processing (NLP), understanding the structure of text is crucial. The turian/flair-pos-english Cognitive Actions provide developers with a powerful tool to perform Part-of-Speech (POS) tagging using the state-of-the-art Flair embeddings and LSTM-CRF model. By leveraging these pre-built actions, developers can easily analyze sentence structures and extract valuable linguistic information from their applications.

Prerequisites

Before you start using the Cognitive Actions, ensure that you have the following:

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Basic understanding of JSON format, as the input and output will be in JSON.

Authentication is typically handled by including the API key in the request headers, allowing secure access to the actions.

Cognitive Actions Overview

Run POS Tagging with Flair

The Run POS Tagging with Flair action executes the Flair POS tagging model on a JSON list of sentence strings to identify parts of speech. This action falls under the category of named-entity-recognition, making it a valuable addition for any application dealing with text analysis.

Input

The input for this action requires a JSON object with the following fields:

  • sentencesJson (required): A JSON-encoded array of sentence strings that are used for part-of-speech tagging.
  • miniBatchSize (optional): Specifies the batch size used in the flair.predict method, with a default value of 32.

Example Input:

{
  "sentencesJson": "[\"I love berlin.\", \"Deep neural networks are cool.\", \"Geoff Hinton is the father---Yoshua Bengio is the son---Yann LeCun is the holy ghost.\"]"
}

Output

The output of this action is a list of JSON dictionaries representing the results for each processed sentence. Each entry includes:

  • text: The original sentence.
  • all labels: An array of objects containing the predicted POS tags and their confidence scores.
  • token positions: The positions of each token in the sentence.

Example Output:

[
  {
    "text": "I love berlin.",
    "all labels": [
      { "value": "PRP", "confidence": 0.9999994039535522 },
      { "value": "VBP", "confidence": 0.9999959468841553 },
      { "value": "NN", "confidence": 0.6081387996673584 },
      { "value": ".", "confidence": 0.9999886751174927 }
    ],
    "token positions": [[0, 1], [2, 6], [7, 13], [13, 14]]
  },
  ...
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how you might call this action using Python:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "b39c0662-9ec9-4d64-b8e4-665fe29e0fdf"  # Action ID for Run POS Tagging with Flair

# Construct the input payload based on the action's requirements
payload = {
    "sentencesJson": "[\"I love berlin.\", \"Deep neural networks are cool.\", \"Geoff Hinton is the father---Yoshua Bengio is the son---Yann LeCun is the holy ghost.\"]"
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload}  # Hypothetical structure
    )
    response.raise_for_status()  # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this code snippet, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The action ID and input payload are structured according to the requirements, and the response is handled gracefully to provide feedback.

Conclusion

The turian/flair-pos-english Cognitive Actions offer developers a robust way to integrate advanced POS tagging capabilities into their applications. With just a few lines of code, you can extract meaningful linguistic details from text, enhancing your NLP projects. Consider exploring additional use cases or combining this action with other cognitive functionalities to expand your application’s capabilities.

← Back to All Articles