Text Mining: Document Embeddings

[@davidcooper4327]

Love your videos!! Question: Is it possible to pickle the text preprocessor? If I wanted to deploy your example, I would have to build the preprocessor and embedding from scratch. Is that correct?

[@muhammadnurfahmi9530]

where can i get the dataset to hands on

[@gtsmeg3474]

How the document embedding process work ?

[@dmitryungurean]

Hello guys, what is the best place to submit the following error and to find solution? "Corpus" widget is not working:( I get the following error Can't read file (Cannot parse dataset C:\Users\DUngurean\AppData\Local\Programs\Orange\lib\site-packages\orangecontrib\text\datasets\grimm-tales-selected.tab: Cannot cast ufunc '__contains__ (vectorized)' output from dtype('O') to dtype('bool') with casting rule 'same_kind')

[@OrangeDataMining]

Best to report it to our issue tracker or on our Discord. Thanks!

[@benjaminreuse6723]

please tutorials of pubmed widget text mining

[@zoni36]

Videos 16-18 are tutorials on text mining