arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.08284cs.CL
收藏

面向问答的结构化知识落地

Structured Knowledge Grounding for Question Answering

University of California, Santa Barbara(加州大学圣巴巴拉分校);Kent School(肯特学校)

Yujie Lu, Siqi Ouyang, Kairui Zhou

AI总结:

本文提出仅依靠语言模型结合动态跳数知识检索与深度融合机制完成知识型问答,并在 CommensenseQA 上达到最先进性能。

摘要:

语言模型(LM)能否通过内在的关系推理能力,将问答(QA)任务落地到知识库中?尽管以往仅使用 LM 的模型已在许多 QA 任务上取得一定成功,但近期方法引入知识图谱(KG),以其更具逻辑驱动性的隐式知识补充 LM。然而,如何有效从 KG 等结构化数据中提取信息、从而增强 LM,仍是一个悬而未决的问题,当前模型依赖图技术来提取知识。本文提出仅利用 LM 将语言与知识结合,以灵活性、覆盖广度和结构化推理来完成基于知识的问答。具体而言,我们设计了一种知识构建方法,通过动态跳数检索相关上下文,相比传统基于 GNN 的技术表现出更强的全面性。我们还设计了深度融合机制,进一步打通语言与知识之间信息交换的瓶颈。大量实验表明,我们的模型在 CommensenseQA 基准上持续展现出最先进性能,证明了仅利用 LM 将 QA 稳健地落地到知识库中的可能性。

英文摘要:

Can language models (LM) ground question-answering (QA) tasks in the knowledge base via inherent relational reasoning ability? While previous models that use only LMs have seen some success on many QA tasks, more recent methods include knowledge graphs (KG) to complement LMs with their more logic-driven implicit knowledge. However, effectively extracting information from structured data, like KGs, empowers LMs to remain an open question, and current models rely on graph techniques to extract knowledge. In this paper, we propose to solely leverage the LMs to combine the language and knowledge for knowledge based question-answering with flexibility, breadth of coverage and structured reasoning. Specifically, we devise a knowledge construction method that retrieves the relevant context with a dynamic hop, which expresses more comprehensivenes than traditional GNN-based techniques. And we devise a deep fusion mechanism to further bridge the information exchanging bottleneck between the language and the knowledge. Extensive experiments show that our model consistently demonstrates its state-of-the-art performance over CommensenseQA benchmark, showcasing the possibility to leverage LMs solely to robustly ground QA into the knowledge base.

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。

↑