How can an RNN be used for detecting toxic spans (spans of words containing toxic language) in a social media comment? Specifically, what should be the input to the RNN at each time step t? How many outputs (i.e., yˆ) are produced given a comment containing n words? What is each yˆ(t) a probability distribution over?

  • $\begingroup$ Welcome to CS.SE! What research have you done? Have you done a literature search? There are papers in the research literature on this subject -- I suggest reading them, them seeing if you still have a specific question, and if you do, show some background on what you've found so far and what sources you've read. Making your question useful for others by showing your research helps both the site and helps you ask a better question, and might make it more likely you get a useful answer. $\endgroup$ – D.W. Mar 26 at 19:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.