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：当前不完整话语重写（IUR）方法未能捕获重要词语的来源，而这一信息对于编辑不完整话语至关重要，且方法会引入无关话语中的词语。我们提出了一种新颖且有效的多任务信息交互框架，包含上下文选择、编辑矩阵构建及相关性融合，以捕获多粒度语义信息。通过提取相关话语并识别重要词语，我们的方法在该领域两个基准数据集Restoration-200K和CANAND上超越了现有最先进模型。代码将提供于\url{https://github.com/yanmenxue/QR}。