论文标题
基于不监督的基于对齐的迭代证据检索多跳问题的回答
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
论文作者
论文摘要
证据检索是提问回答（QA）的关键阶段，不仅需要提高绩效，而且要解释相应的QA方法的决定。我们介绍了一种简单，快速和无监督的迭代证据检索方法，该方法依赖于三个想法：（a）一种无监督的对准方法，通过仅使用手套嵌入的方式使用仅使用手套的句子进行宽松的问题和答案，（b）迭代过程，该过程不得不在现有的术语中进行重新审查，而该术语不再涉及该术语，该术语终于被赋予该术语（cription），该术语终止了（c），该术语（c）的范围（c）（c）的术语（c）（c），该术语是始终如一的（c）（c），该术语（c）的术语（c）（c）的术语（c）（c）的术语（c）（c），该术语是始终如一的（c）。候选人的答案被检索到的理由所涵盖。尽管它很简单，但我们的方法在两个数据集上的证据选择任务上的所有先前方法（包括监督方法）都超过了：MultiRC和QASC。当这些证据句子被送入罗伯塔答案分类部分时，我们在这两个数据集中实现了最先进的质量检查性能。
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.
