[Python] How to correctly identify entity types for tokens using spaCy using python?

I'm using spaCy to extract and identify entity types (like ORG, GPE, DATE, etc.) from a text description. However, I am noticing some incorrect results, and I'm unsure how to fix this.

Here is the code I am using:

import spacy

nlp = spacy.load("en_core_web_sm")

def getPayeeName(description):
description = description.replace("-", " ").replace("/", " ").strip()
doc = nlp(description)

for token in doc:
print(f"Token: {token.text}, Entity: {token.ent_type_ if token.ent_type_ else 'None'}")

# Example input
description = "UPI DR 400874707203 BENGALORE 08 JAN 2024 14:38:56 MEDICAL LTD HDFC 50200"
getPayeeName(description)


Token: UPI, Entity: ORG

Token: DR, Entity: ORG

Token: 400874707203, Entity: None

Token: BENGALORE, Entity: None

Token: 08, Entity: DATE

Token: JAN, Entity: DATE

Token: 2024, Entity: DATE

Token: 14:38:56, Entity: None

Token: MEDICAL, Entity: ORG

Token: LTD, Entity: ORG

Token: HDFC, Entity: ORG

Token: 50200, Entity: ORG

• 
  50200 is identified as ORG, but it is just a number.
  
  
• 
  BENGALORE is a city, but it is not recognized as a GPE or location (returns None).
  
  
• 
  UPI and DR are acronyms/abbreviations, but they are incorrectly identified as ORG.
  

I want the entity recognition to be more accurate and reliable. How can I fix these issues? Are there additional spaCy configurations, custom rules, or pre-trained models I should use to improve the entity recognition?

Note: I tried ChatGPT as well, but still this issue is not solved.

Continue reading...