Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 395 Bytes

README.md

File metadata and controls

2 lines (2 loc) · 395 Bytes

Some work I did for a client in middle east - sanitized content. Was for understanding natural language so I used NLTK which seems to have less overhead for learning than spaCy and I had a tight deadline.

Shows NLP pipeline for accomplishing the ngram analysis to best of ability. Some bottleneck was my lack of complete knowledge in regex to help thread out the results at the time.