MultiRC

AbstractRemarkable success has been achieved in the last few years on some limited machine reading comprehension (MRC) tasks. However, it is still difficult to interpret the predictions of existing MRC …...

AbstractReading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge. Just as the process of knowledge accumulation is time-consuming for human readers, it is …...

AbstractThis paper focuses on the topic of inferential machine comprehension, which aims to fully understand the meanings of given text to answer generic questions, especially the ones needed reasoning skills. …...

AbstractQuestion Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple …...

AbstractSelecting input features of top relevance has become a popular method for building self-explaining models. In this work, we extend this selective rationalization approach to text matching, where the goal …...

AbstractEvidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the QA method. We introduce a simple, …...

AbstractMulti-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first …...

AbstractLearning from rationales seeks to augment model prediction accuracy using human-annotated rationales (i.e. subsets of input tokens) that justify their chosen labels, often in the form of intermediate or multitask …...