通过双视角关键词引导，提升多跳问答生成精度
Multi-Hop Question Generation via Dual-Perspective Keyword Guidance
- 区分问题关键词与文档关键词，分别捕捉提问意图和内容关联
- 构建双解码器框架，使关键词与问题生成协同优化
- 在多个基准上表现优异，适合需要精准信息整合的任务
多跳问题生成（MQG）旨在生成需综合文档中多个信息片段才能回答的问题。核心挑战在于有效定位与问答对相关的关键信息片段，通常依赖关键词。然而现有方法未能充分挖掘关键词的引导潜力，且未区分问题关键词与文档关键词的不同作用。为此，本文定义了双视角关键词（即问题关键词与文档关键词），提出双视角关键词引导（DPKG）框架，将关键词无缝融入多跳问题生成过程。我们认为，问题关键词反映提问者意图，文档关键词则体现问答对相关内容。功能上，两者共同定位文档中的关键信息片段，且问题关键词必须出现在生成的问题中。DPKG框架包含一个扩展的Transformer编码器及两个答案感知的Transformer解码器，分别用于关键词与问题生成。大量实验表明该方法有效，展现出优异性能，凸显其在MQG任务中的重要价值。
原文摘要 · Abstract (English)
Multi-hop question generation (MQG) aims to generate questions that require synthesizing multiple information snippets from documents to derive target answers. The primary challenge lies in effectively pinpointing crucial information snippets related to question-answer (QA) pairs, typically relying on keywords. However, existing works fail to fully utilize the guiding potential of keywords and neglect to differentiate the distinct roles of question-specific and document-specific keywords. To address this, we define dual-perspective keywords (i.e., question and document keywords) and propose a Dual-Perspective Keyword-Guided (DPKG) framework, which seamlessly integrates keywords into the multi-hop question generation process. We argue that question keywords capture the questioner's intent, whereas document keywords reflect the content related to the QA pair. Functionally, question and document keywords work together to pinpoint essential information snippets in the document, with question keywords required to appear in the generated question. The DPKG framework consists of an expanded transformer encoder and two answer-aware transformer decoders for keyword and question generation, respectively. Extensive experiments demonstrate the effectiveness of our work, showcasing its promising performance and underscoring its significant value in the MQG task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。