New to NLP: Various questions

• spaCy

  107 28,789 9.2 Python

  💫 Industrial-strength Natural Language Processing (NLP) in Python

  

Stemming removes suffixes and the result is not necessarily a word. Lemmatization gives the word from it's derived. Spacy doesn't even have stemming as the creator doesn't consider it useful.

• huggingface_hub

  104 1,704 9.6 Python

  The official Python client for the Huggingface Hub.

  

Bag of words (BoW) is quite old, word2vec is oldish (2013), but they can still perform well enough, depending on what you want to do. FastText is also "old" (2016), even though it's a very good baseline and it's actually kinda based on a bag of words model and the skipgram model that was introduced with the word2vec paper. The hot new thing is HuggingFace and the BERT family of models, but they are orders of magnitude more resource intensive.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project