arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14813cs.CL
收藏

ENT-DESC:基于知识图谱的实体描述生成

ENT-DESC: Entity Description Generation by Exploring Knowledge Graph

DAMO Academy, Alibaba Group(阿里巴巴达摩院);Singapore University of Technology and Design(新加坡科技设计大学);York University(约克大学)

Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu, Luo Si

摘要:

以前的工作知识到文本生成作为输入的几个RDF三元组或键值对传达一些实体的知识,以生成一个自然语言描述。现有的数据集,如WIKIBIO,WebNLG和E2 E,基本上在输入三元组/配对集及其输出文本之间具有良好的对齐。然而,在实践中,输入的知识可能是足够的,因为输出描述可能只涵盖最重要的知识。在本文中,我们引入了一个大规模的和具有挑战性的数据集,以促进在KG到文本这样一个实际的情况下的研究。我们的数据集涉及从一个大的知识图谱(KG)中检索各种类型的主要实体的丰富知识,这使得目前的图到序列模型在生成描述时严重遭受信息丢失和参数爆炸的问题。我们通过提出一种能够更全面地表示原始图信息的多图结构来解决这些挑战。此外,我们还采用了聚合方法,学习提取丰富的图形信息。大量的实验证明了我们的模型架构的有效性。

英文摘要:

Previous works on knowledge-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language description. Existing datasets, such as WIKIBIO, WebNLG, and E2E, basically have a good alignment between an input triple/pair set and its output text. However, in practice, the input knowledge could be more than enough, since the output description may only cover the most significant knowledge. In this paper, we introduce a large-scale and challenging dataset to facilitate the study of such a practical scenario in KG-to-text. Our dataset involves retrieving abundant knowledge of various types of main entities from a large knowledge graph (KG), which makes the current graph-to-sequence models severely suffer from the problems of information loss and parameter explosion while generating the descriptions. We address these challenges by proposing a multi-graph structure that is able to represent the original graph information more comprehensively. Furthermore, we also incorporate aggregation methods that learn to extract the rich graph information. Extensive experiments demonstrate the effectiveness of our model architecture.

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。

↑