Evaluation

NLP Pipeline

In comparison to general machine learning pipelines, In NLP we need to perform some extra processing steps. The region is very simple that machines don’t understand the text. Here our biggest problem is How to make the text understandable for machines. Some of the most common problems we face while performing NLP tasks are mentioned below....

1. Data Acquisition :

As we know, For building the machine learning model we need data related to our problem statements, Sometimes we have our data and Sometimes we have to find it. Text data is available on websites, in emails, in social media, in form of pdf, and many more. But the challenge is. Is it in a machine-readable format? if in the machine-readable format then will it be relevant to our problem? So, First thing we need to understand our problem or task then we should search for data. Here we will see some of the ways of collecting data if it is not available in our local machine or database....

2. Text Cleaning :

Sometimes our acquired data is not very clean. it may contain HTML tags, spelling mistakes, or special characters. So, let’s see some techniques to clean our text data....

3. Text Preprocessing:

...

4 . Feature Engineering:

...

5. Model Building:

NLP software mainly works at the sentence level and it also expects words to be separated at the minimum level....

6. Evaluation :

...

7. Deployment

In Feature Engineering, our main agenda is to represent the text in the numeric vector in such a way that the ML algorithm can understand the text attribute. In NLP this process of feature engineering is known as Text Representation or Text Vectorization....