Timeline for Is it a good idea to transform a sequence classification problem into simple classification problem with this way?
Current License: CC BY-SA 3.0
9 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Dec 29, 2017 at 0:38 | comment | added | tired and bored dev | @damdam092 I've added some more information on bag of words, and n-grams which tries to account of words that appear together. | |
Dec 29, 2017 at 0:36 | history | edited | tired and bored dev | CC BY-SA 3.0 |
Added some information on bag of words and n-grams.
|
Dec 28, 2017 at 7:11 | history | edited | tired and bored dev | CC BY-SA 3.0 |
added 5 characters in body
|
Dec 28, 2017 at 7:11 | comment | added | tired and bored dev | True. HMMs and CRFs are used in regular NLP. I was thinking about bag of words models.... | |
Dec 27, 2017 at 14:35 | comment | added | Jakub Bartczuk | "In fact in regular (Not deep learning)NLP problems, they convert sequence problems to regular classification problems." This is an overstatement. Many NLP tasks used structured prediction algorithms like HMMs or Conditional Random Fields before RNNs became state-of-the-art | |
Dec 26, 2017 at 10:25 | vote | accept | ChiPlusPlus | ||
Dec 26, 2017 at 9:11 | comment | added | tired and bored dev | Yes. They usually do. More than what you would need for regular classification algorithm. | |
Dec 26, 2017 at 8:30 | comment | added | ChiPlusPlus | Does RNNs require massive amoubt of data to be trained? | |
Dec 26, 2017 at 8:04 | history | answered | tired and bored dev | CC BY-SA 3.0 |