News for hackers. Stuff that matters.
Re:Understanding word vectors by akhilcacharya on Friday March 02, 2018 @09:49PM (#16507581)
I'm working on a problem kinda similar to that with a binary classification on a class imbalanced dataset, but fastText and Bidirectional LSTMs appear to work pretty terribly even with oversampling. Is there a better alternative?
Re:Understanding word vectors by wenc on Friday March 02, 2018 @10:32PM (#16507679)
Class imbalance is a tricky problem, but it is unrelated to FastText.

There is no silver bullet. The best solution is to collect more data to bring the classes to a balance. The second best approach is to try algorithms like SMOTE.

Re:Understanding word vectors by kk58 on Saturday March 03, 2018 @01:56AM (#16508256)
SMOTE is for more numerical data.
Re:Understanding word vectors by wenc on Saturday March 03, 2018 @09:15AM (#16509327)
It is a numerical problem underneath. Word vectors are numerical vectors.