Processing Text with Python Essential Training
The LinkedIn learning course talks about text processing or natural language processing using Python with Natural Language Toolkit. The course talks about what is considered a document, corpus, stemming, lemmatization, a few other aspects of language processing. A document can be a log file, a social media post, or a review that contains text about a specific context. A corpus is a combination of similar documents. Stemming is the processing of keeping only the stem or base word, however, this method may return incomplete words. On other hand, lemmatization is the process of keeping a base word that is complete, however this method requires a dictionary and other resources which makes it more expensive to run.
Overall, this course taught me about data-mining, word processing, and NLTK framework where I will be able to use in a future project as well as improving my knowledge of how LLM works.