arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.05798cs.CLcs.AI
收藏

BigText-QA:基于大规模混合知识图谱的问答

BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph

University of Luxembourg(卢森堡大学);International Institute of Information Technology (IIIT), Bangalore(班加罗尔国际信息技术研究所)

Jingjing Xu, Maria Biryukov, Martin Theobald, Vinu Ellampallil Venugopal

AI总结:

BigText-QA 提出一种集成问答方法,通过构建统一表示结构化与非结构化知识的混合知识图谱,结合命名实体映射与文本子句的丰富上下文,在复杂问答任务中优于 DrQA 并与 QUEST 取得相当结果。

摘要:

在文本资源上回答复杂问题仍然是一个挑战,特别是在处理自然语言句子中表达的多个实体之间的细微关系时。为此,像 YAGO、DBpedia、Freebase 和 Wikidata 这样精心整理的知识库(KB)已被广泛使用,并在过去十年中在问答(QA)应用中获得了极大的认可。虽然这些知识库提供了结构化的知识表示,但它们缺乏自然语言来源中丰富的上下文多样性。为了解决这一局限性,BigText-QA 引入了一种集成问答方法,该方法能够基于一种更具冗余性的知识图谱(KG)形式来回答问题,这种知识图谱以统一的图形表示组织结构化和非结构化(即“混合”)知识。因此,BigText-QA 能够结合两者的优势——一组规范化的命名实体,映射到结构化的背景知识库(如 YAGO 或 Wikidata),以及一组开放式的文本子句,提供高度多样化的关系释义和丰富的上下文信息。我们的实验结果表明,BigText-QA 优于基于神经网络的问答系统 DrQA,并取得了与基于图的无监督问答系统 QUEST 相当的结果。

英文摘要:

Answering complex questions over textual resources remains a challenge, particularly when dealing with nuanced relationships between multiple entities expressed within natural-language sentences. To this end, curated knowledge bases (KBs) like YAGO, DBpedia, Freebase, and Wikidata have been widely used and gained great acceptance for question-answering (QA) applications in the past decade. While these KBs offer a structured knowledge representation, they lack the contextual diversity found in natural-language sources. To address this limitation, BigText-QA introduces an integrated QA approach, which is able to answer questions based on a more redundant form of a knowledge graph (KG) that organizes both structured and unstructured (i.e., "hybrid") knowledge in a unified graphical representation. Thereby, BigText-QA is able to combine the best of both worlds$\unicode{x2013}$a canonical set of named entities, mapped to a structured background KB (such as YAGO or Wikidata), as well as an open set of textual clauses providing highly diversified relational paraphrases with rich context information. Our experimental results demonstrate that BigText-QA outperforms DrQA, a neural-network-based QA system, and achieves competitive results to QUEST, a graph-based unsupervised QA system.

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。

↑