一种融合文本与知识图谱的问答系统模型
A question answering system model integrating text and knowledge graph
张佳豪 1黄勃 1王晨明 1曾国辉 1刘瑾1
作者信息
- 1. 上海工程技术大学电子电气工程学院,上海 201620
- 折叠
摘要
知识图谱是实现开放领域问答的关键技术之一,开放领域问答任务往往需要足够多的知识信息,而知识图谱的不完备性成为制约问答系统性能的重要因素.利用外部非结构化的文本与基于知识图谱的结构化知识相结合填补缺失信息时,检索外部文本的准确性和效率尤为关键,选取与问题相关度较高的文本可提升系统性能.相反,选取与问题相关性较弱的文本将引入知识噪声,降低问答任务的准确性.因此,设计了一种融合文本与知识图谱的问答系统模型,其中的文本检索器可充分挖掘问题和文本的语义信息,提高检索质量和查询子图的准确性;知识融合器将文本和知识库中的知识结合构建知识的融合表征.实验结果表明,相较对比模型,该模型在性能上存在一定优势.
Abstract
Knowledge graph is one of the key technologies to realize question answering in open domain. Open domain question answering tasks often require enough knowledge information,and the incompleteness of knowledge graph becomes an important factor restricting the performance of question answering system. When combining external unstructured text with structured knowledge based on knowledge graphs to fill in missing information,the accuracy and efficiency of retrieving external texts are particularly critical,and selecting texts that are highly relevant to the problem can improve system performance. Conversely,selecting texts that are less relevant to the question will introduce knowledge noise,thereby reducing the accuracy of question answering tasks. Therefore,this paper designs a question answering system model that integrates text and knowledge graph,in which the text retriever can fully mine the semantic information of questions and texts to improve the quality of retrieval and the accuracy of query subgraphs. The knowledge mixer can combine knowledge from text and knowledge bases to build fusion representations of knowledge. The experimental results show that the proposed model has certain advantages in performance compared with the comparison models.
关键词
问答系统/知识图谱/外部知识/文本检索/融合表征Key words
question answering system/knowledge graph/external knowledge/text retrieval/fusion representation引用本文复制引用
基金项目
科技创新2030"新一代人工智能"重大项目(2020AAA0109300)
国家自然科学基金青年项目(61802251)
出版年
2024
国家科技期刊平台
NSTL
万方数据