Long-Distance Dependencies Don't Have to Be Long: Simplifying through Provably (Approximately) Optimal Permutations

ACL 2019 Rishi Bommasani

Neural models at the sentence level often operate on the constituent words/tokens in a way that encodes the inductive bias of processing the input in a similar fashion to how humans do. However, there is no guarantee that the standard ordering of words is computationally efficient or optimal... (read more)

PDF Abstract

Evaluation results from the paper


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