Here are some interesting results:
Anything I should add to my reading list?
Filed under Uncategorized
Maybe check into word/sentence/paragraph/document embeddings as a precursor for clustering.
Like word2vec? https://www.tensorflow.org/tutorials/word2vec
Yep, that’s a good place to start. I think the latest thing is to be able to summarize larger chunks of text with some sort of attention model.