써니 노트 써니 노트

머신러닝 || 딥러닝/NLP

• Python libraries for NLP

  머신러닝 || 딥러닝/NLP 2022. 11. 10. 17:48

  NLTK : Natural Language Toolkit It is a suite of text processing libraries (i.e. tokenization, stemming, tagging, parsing) and it includes more than 50 corpora and lexical sources such as WordNet, the Penn Treebank Corpus etc.

  Read More
• Text preprocessing

  머신러닝 || 딥러닝/NLP 2022. 11. 5. 21:17

  https://stackoverflow.com/questions/54396405/how-can-i-preprocess-nlp-text-lowercase-remove-special-characters-remove-numb

  Read More
• [Gensim] pre-trained model / model training 셋업 with Gensim

  머신러닝 || 딥러닝/NLP 2022. 10. 31. 20:22

  Where to download pre-trained model from gensim https://github.com/RaRe-Technologies/gensim-data https://huggingface.co/models?other=gensim load pre-trained model using gensim.downloader.load https://radimrehurek.com/gensim/models/word2vec.html https://kavita-ganesan.com/easily-access-pre-trained-word-embeddings-with-gensim/#.Y1_HIOzMK3I load pre-trained model using API https://radimrehurek.com/..

  Read More
• [resources] NLP 공부 리소스

  머신러닝 || 딥러닝/NLP 2022. 9. 19. 19:50

  Lecture NLP ETH : https://rycolab.io/classes/intro-nlp-f22/ 책 NLP [Eisenstein] : https://github.com/jacobeisenstein/gt-nlp-class/blob/master/notes/eisenstein-nlp-notes.pdf

  Read More