Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from irrelevant utterances. We propose a novel and effective multi-task information interaction framework including context selection, edit matrix construction, and relevance merging to capture the multi-granularity of semantic information. Benefiting from fetching the relevant utterance and figuring out the important words, our approach outperforms existing state-of-the-art models on two benchmark datasets Restoration-200K and CANAND in this field. Code will be provided on \url{https://github.com/yanmenxue/QR}.

翻译：近年来，不完整语句改写（IUR）方法未能有效捕获关键词语的源头信息，而这对编辑不完整语句至关重要，同时这些方法还常常引入无关语句中的词汇。为此，我们提出一种新颖且高效的多任务信息交互框架，该框架融合了上下文选择、编辑矩阵构建及相关性合并三个模块，以捕获多粒度语义信息。得益于提取相关语句并定位关键词语，我们的方法在领域内两个基准数据集 Restoration-200K 和 CANAND 上均优于现有最先进模型。相关代码将发布于 \url{https://github.com/yanmenxue/QR}。