Which Python package is built for tokenization, tagging and named entity recognition?
Why A is the answer
spaCy
spaCy is a natural language package. NumPy handles arrays.
In detail
- spaCy is built for language tasks such as tagging and entity recognition.
- It offers tokenization and tagging too.
Use case
An illustrative scenario, not a real incident.
A team extracts names from emails with spaCy's named entity recognition.
See it in different ways
mindmap
root((ML basics))
Labeled data
Classification
Regression
Unlabeled data
Clustering
Validation
Cross validation
Held-out test setflowchart LR S0["Text"] --> S1["Tokenize"] --> S2["Tag"] --> S3["Find entities"]
Key point: spaCy is a language processing package.
Why the other options are wrong
- B. NumPy
- NumPy handles arrays.
- C. Matplotlib
- Matplotlib draws charts.
- D. Requests
- Requests makes HTTP calls.