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 2104.01569cs.CL
收藏

基于Transformer和图注意力网络的知识图谱会话问答

Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks

University of Bonn(波恩大学);Technische Universität Darmstadt(达姆施塔特工业大学);Zerotha Research(Zerotha研究院);Cerence GmbH(赛轮思有限公司);Osthus GmbH(Osthus有限公司);Fraunhofer IAIS(弗劳恩霍夫智能分析与信息系统研究所)

Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova

摘要:

本文研究了基于知识图谱的(复杂)会话式问答问题。为此,我们提出了LASAGNE(muLti-task语义解析with Transformer and Graph attenNtion nEtworks)。这是第一种方法,它采用了一个Transformer架构扩展与图形注意力网络的多任务神经语义解析。LASAGNE使用一个Transformer模型来生成基本的逻辑形式,而Graph Attention模型用于利用(实体)类型和谓词之间的相关性来生成节点表示。LASAGNE还包括一个新的实体识别模块,它可以检测、链接和排名问题上下文中的所有相关实体。我们评估LASAGNE在标准数据集上进行复杂的顺序问答,在所有问题类型上都优于现有的基线平均值。具体来说,我们表明,LASAGNE提高了10个问题类型中的8个的F1分数;在某些情况下,与最先进的技术相比,F1分数的增加超过20%。

英文摘要:

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

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。

↑