How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking

30 Apr 2020Nicola De CaoMichael SchlichtkrullWilker AzizIvan Titov

Attribution methods assess the contribution of inputs (e.g., words) to the model prediction. One way to do so is erasure: a subset of inputs is considered irrelevant if it can be removed without affecting the model prediction... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper