Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
This addresses the challenge of biased supervision in abductive reasoning for NLP applications, though it is incremental as it builds on existing zero-shot and regularization techniques.
The paper tackles the problem of abductive commonsense reasoning in NLP by proposing an unsupervised method that uses posterior regularization to enforce mutual exclusion among explanations, avoiding subjective annotations. The results show it outperforms or matches zero-shot pretrained language models and other knowledge-augmented methods on diverse datasets.
Abductive reasoning aims to find plausible explanations for an event. This style of reasoning is critical for commonsense tasks where there are often multiple plausible explanations. Existing approaches for abductive reasoning in natural language processing (NLP) often rely on manually generated annotations for supervision; however, such annotations can be subjective and biased. Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context. The method uses posterior regularization to enforce a mutual exclusion constraint, encouraging the model to learn the distinction between fluent explanations and plausible ones. We evaluate our approach on a diverse set of abductive reasoning datasets; experimental results show that our approach outperforms or is comparable to directly applying pretrained language models in a zero-shot manner and other knowledge-augmented zero-shot methods.