arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14781cs.CL
收藏

基于结构增强的文本表示学习的高效知识图谱构建

Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion

School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);International Center of Future Science, Jilin University(吉林大学未来科学国际中心)

Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang

摘要:

人工组织的知识图谱为各种自然语言处理任务提供了关键的支持信息,但这些图谱通常是不完整的,促使自动完成它们。流行图嵌入方法,例如,transE,通过将图元素表示为密集嵌入并捕获它们与空间距离的三级关系来学习结构化知识。然而,它们很难推广到训练中从未访问过的元素,并且本质上容易受到图不完整性的影响。相反,文本编码方法,例如,KG-BERT,诉诸图三元组的文本和三层上下文表示。它们具有足够的可推广性,并且对不完整性具有鲁棒性,特别是当与预先训练的编码器相结合时。但有两个主要的缺点限制了性能:(1)由于推理中所有可能的三元组的评分成本高,开销大;(2)文本编码器中缺乏结构化知识。在本文中,我们遵循文本编码范式,旨在通过使用图嵌入技术来增强它来减轻其缺点-这两种范式的互补混合。具体来说,我们将每个三元组划分为两个不对称的部分,如基于映射的图嵌入方法,并通过暹罗风格的文本编码器将这两个部分编码为上下文表示。建立在表示,我们的模型采用确定性分类器和空间测量表示和结构学习分别。此外,我们开发了一个自适应集成方案,以进一步提高性能,将三重评分从现有的图嵌入模型。在实验中,我们在三个基准测试和一个链接预测的zero-shot数据集上实现了最先进的性能,与文本编码方法相比,推理成本降低了1-2个数量级。

英文摘要:

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them. Prevalent graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements into dense embeddings and capturing their triple-level relationship with spatial distance. However, they are hardly generalizable to the elements never visited in training and are intrinsically vulnerable to graph incompleteness. In contrast, textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations. They are generalizable enough and robust to the incompleteness, especially when coupled with pre-trained encoders. But two major drawbacks limit the performance: (1) high overheads due to the costly scoring of all possible triples in inference, and (2) a lack of structured knowledge in the textual encoder. In this paper, we follow the textual encoding paradigm and aim to alleviate its drawbacks by augmenting it with graph embedding techniques -- a complementary hybrid of both paradigms. Specifically, we partition each triple into two asymmetric parts as in translation-based graph embedding approach, and encode both parts into contextualized representations by a Siamese-style textual encoder. Built upon the representations, our model employs both deterministic classifier and spatial measurement for representation and structure learning respectively. Moreover, we develop a self-adaptive ensemble scheme to further improve the performance by incorporating triple scores from an existing graph embedding model. In experiments, we achieve state-of-the-art performance on three benchmarks and a zero-shot dataset for link prediction, with highlights of inference costs reduced by 1-2 orders of magnitude compared to a textual encoding method.

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。

↑