NLP Models and NLP Tasks

In this series of NLP Learnings, the previous post  Natural Language Processing Primer we have learned about NLP Models. Re-defining in this post, NLP models are prediction functions or prediction constructs.

Each NLP Model (or construct) core behavior will vary considerably based on the nature of the NLP task like classification or regression or statistical metrics or others (see below some of the overall NLP tasks).

We use these NLP models along with input training and test data as a reference and extend them by adding more steps to the NLP input models to meet our NLP business requirements. Alternatively, create your own NLP models and analyze your model performance against the reference model metrics or performance.

So it is very important to understand whether an input NLP model “works” 
or is “good” for your NLP requirements solution.

NLP Tasks List (only a few are listed below)

1. Classification Tasks
2. Regression Tasks
3. Statistical Tasks
4. Deep Learning Tasks
5. Ranking Tasks

Above NLP models tasks either does "deep analysis" or "shallow analysis" 
of your business requirement input data.

Evaluating NLP Models – Know Possible Metrics

As mentioned above, how do you know whether an input NLP model “works” or is “good” for your NLP requirements solution?

One way to evaluate your NLP model is by comparing and evaluating the "Metrics" 
of your NLP model against another models using the same your dataset.

Following are the various metrics you can use to evaluate the NLP models these metrics are based on:

1. Accuracy, Prediction, F-Score

2, Mean Standard Error, MAE (Mean Absolute Error)

3, Correlation

4. Interception Score, Fréchet Inception Distance

5. Ranking Metrics:

• MRR (Mean Reciprocal Rank)
• Precision at K
• DCG (Discounted Cumulative Gain) & NDCG (Normalized Discounted Cumulative Gain)
• MAP (Average Precision and Mean Average Precision)
• Kendall’s tau
• Spearman’s rho

The below diagram provides a visual representation of the above knowledge.

 

Related Topics:

1. Natural Language Processing Primer
2. NLP Learnings 02 – After Primer – NLP Models & Evaluating NLP Models
3. NLP Learnings 03 – What is Linguistic in NLP and Linguistic Categories or Linguistic Levels
4. NLP Learnings 04 – Sentence Linguistic Analysis – Words As First Step
5. NLP Learnings 05 – Sentence Linguistic Analysis – Pragmatics Analysis
6. NLP Learnings 06 – What can we do with A Sentence in NLP Tasks
7. NLP Learnings 07 – Introducing NLP Language Models
8. NLP Learnings 08 – Language Models – Probability Types
9. NLP Learnings 09 – Language Models – Measuring Text Based On Probability
10. NLP Learnings 10 – Language Models – Defining Word Boundaries
11. NLP Learnings 11 – Language Models – Your Business Text Data and Their Words Representation
12. NLP Learnings 12 – Language Models – Regularization Techniques And Your Business Text Data
13. NLP Learnings 13 – Language Models – Smoothing Regularization Techniques And Your Business Text Data
14. NLP Learnings 14 – Language Models – NLP Key Terms and Concepts
15. NLP Learnings 15 – Language Models – Classifiers Introduction
16. NLP Learnings 16 – Language Models – Classifiers – What are Probabilistic Classifiers
17. NLP Learnings 17 – Language Models – Classifiers – Simple Classifiers Introduction
18. NLP Learnings 18 – Language Models – Classifiers – Simple Classifiers – Linear Probabilistic Classifier Introduction
19. NLP Learnings 19 – Language Models – Classifiers – Evaluating Classifiers – Precision Recall F-Score Confusion Matrix
20. NLP Learnings 20 – Language Models – Classifiers – Represent Words In A Document – Choosing and Representing Features In The Right Way
21. NLP Learnings 21 – Language Models – Word Embeddings
22. NLP Learnings 22 – Language Models – Sentence and Document Embeddings
23. NLP Learnings 23 – Language Models – Sentence and Document Embeddings – Which one to consider