/NLP

Paragraph Embedding

Text Embedding-related Questions

Q: Where to find some Pre-trained Doc2Vec/Word2Vec Models?

https://www.quora.com/Where-can-I-find-some-pre-trained-word-vectors-for-natural-language-processing-understanding

(word-embedding models) https://stackoverflow.com/questions/45310409/using-a-word2vec-model-pre-trained-on-wikipedia

Q: How to use Gensim doc2vec with pre-trained word vectors?

https://stackoverflow.com/questions/27470670/how-to-use-gensim-doc2vec-with-pre-trained-word-vectors

Q: Quick Access - Gensim Documents about Doc2Vec

https://radimrehurek.com/gensim/models/doc2vec.html

(ipynb usage example) https://github.com/RaRe-Technologies/gensim/blob/develop/docs/notebooks/doc2vec-lee.ipynb

Q: Doc2vec get most similar documents?

https://stackoverflow.com/questions/42781292/doc2vec-get-most-similar-documents

STD-CS224N

http://web.stanford.edu/class/cs224n/

LDA Questions

Q1: How to find the optimal number of K topics for LDA modeling?

https://www.machinelearningplus.com/nlp/topic-modeling-gensim-python/#17howtofindtheoptimalnumberoftopicsforlda

Q2: What's the valid input format of data for Gensim LDA models? Only BOW (ID, WORD)?

Text Classification

Q1: Parameter tuning using grid search (sklearn)

https://stats.stackexchange.com/questions/277014/what-parameters-to-optimize-in-knn (for KNN optimization) https://www.pyimagesearch.com/2016/08/15/how-to-tune-hyperparameters-with-python-and-scikit-learn/