arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.07597cs.CL
收藏

面向知识库复杂问题回答的问题分解树

Question Decomposition Tree for Answering Complex Questions over Knowledge Bases

State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室)

Xiang Huang, Sitao Cheng, Yiheng Shu, Yuheng Bao, Yuzhong Qu

AI总结:

针对现有知识库问答问题分解方法仅支持单一组合类型的局限,提出用问题分解树表示复杂问题结构,通过两阶段Clue-Decipher方法生成,构建的QDTQA系统在多个数据集上取得SOTA,还可将现有系统性能提升12%。

摘要:

知识库问答(KBQA)近年来受到广泛关注,尤其是需要多条事实才能回答的复杂问题。问题分解是解决复杂问题的一种极具潜力的方法。现有分解方法仅根据单一组合类型将问题拆分为子问题,这对于涉及多种组合类型的问题而言并不足够。本文提出问题分解树(Question Decomposition Tree,QDT)来表示复杂问题的结构。受自然语言生成(NLG)领域最新进展的启发,我们提出了一种名为Clue-Decipher的两阶段方法来生成QDT,该方法既能利用NLG模型的强大能力,同时又能保留原始问题信息。为验证QDT能够提升KBQA任务效果,我们设计了一个基于分解的KBQA系统,命名为QDTQA。大量实验表明,QDTQA在ComplexWebQuestions数据集上的表现优于此前的最优方法。此外,我们的分解方法将一个现有KBQA系统的性能提升了12%,并在LC-QuAD 1.0上创下了新的最优纪录。

英文摘要:

Knowledge base question answering (KBQA) has attracted a lot of interest in recent years, especially for complex questions which require multiple facts to answer. Question decomposition is a promising way to answer complex questions. Existing decomposition methods split the question into sub-questions according to a single compositionality type, which is not sufficient for questions involving multiple compositionality types. In this paper, we propose Question Decomposition Tree (QDT) to represent the structure of complex questions. Inspired by recent advances in natural language generation (NLG), we present a two-staged method called Clue-Decipher to generate QDT. It can leverage the strong ability of NLG model and simultaneously preserve the original questions. To verify that QDT can enhance KBQA task, we design a decomposition-based KBQA system called QDTQA. Extensive experiments show that QDTQA outperforms previous state-of-the-art methods on ComplexWebQuestions dataset. Besides, our decomposition method improves an existing KBQA system by 12% and sets a new state-of-the-art on LC-QuAD 1.0.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑