ExpBERT: Representation Engineering with Natural Language Explanations
ACL, pp. 2106-2113, 2020.
We show how using these models with natural language explanations can allow us to leverage a richer set of explanations than if we were constrained to only use explanations that can be programmatically evaluated, e.g., through ngram matching or semantic parsing
Suppose we want to specify the inductive bias that married couples typically go on honeymoons for the task of extracting pairs of spouses from text. In this paper, we allow model developers to specify these types of inductive biases as natural language explanations. We use BERT fine-tuned on MultiNLI to ``interpret'' these explanations ...More
PPT (Upload PPT)