arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.02166cs.CL
收藏

大语言模型结合知识图谱解答事实性问题

Large Language Models Meet Knowledge Graphs to Answer Factoid Questions

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Universität Hamburg(汉堡大学);Nazarbayev University(纳扎尔巴耶夫大学);ISP RAS(俄罗斯科学院信息安全问题研究所);Artificial Intelligence Research Institute(人工智能研究院)

Mikhail Salnikov, Hai Le, Prateek Rajput, Irina Nikishina, Pavel Braslavski, Valentin Malykh, Alexander Panchenko

AI总结:

本研究提出结合知识图谱信息的事实性问答方法,通过子图提取、线性化及答案重排序,将预训练Text-to-Text语言模型的Hits@1得分提升4-6%。

摘要:

近期研究表明,将结构化知识融入大语言模型(Large Language Models)可显著提升多种自然语言处理(NLP)任务的效果。本文提出一种方法,探索经知识图谱(Knowledge Graphs)额外信息增强的预训练Text-to-Text语言模型在事实性问题回答中的应用。具体而言,我们提出一种基于问题实体和答案候选的知识图谱子图提取算法,随后通过将提取的子图线性化,利用基于Transformer的模型获取易于解释的信息。最终利用提取的信息对答案候选重新排序,使预训练Text-to-Text语言模型的Hits@1指标提升4-6%。

英文摘要:

Recently, it has been shown that the incorporation of structured knowledge into Large Language Models significantly improves the results for a variety of NLP tasks. In this paper, we propose a method for exploring pre-trained Text-to-Text Language Models enriched with additional information from Knowledge Graphs for answering factoid questions. More specifically, we propose an algorithm for subgraphs extraction from a Knowledge Graph based on question entities and answer candidates. Then, we procure easily interpreted information with Transformer-based models through the linearization of the extracted subgraphs. Final re-ranking of the answer candidates with the extracted information boosts Hits@1 scores of the pre-trained text-to-text language models by 4-6%.

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。

↑