arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.01062cs.CL
收藏

基于梯度表示的知识库扩充组合模型

Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations

Johns Hopkins University(约翰斯·霍普金斯大学);Microsoft Research AI(微软人工智能研究院)

Matthias Lalisse, Paul Smolensky

摘要:

知识库数据的神经模型通常采用图对象的组合表示:实体和关系嵌入被系统地结合起来,以评估候选知识库条目的真实性。使用一个模型的灵感来自谐波语法,我们建议标记三重嵌入,使他们的优化过程中学习良好的知识库三元组的条件。由此产生的模型(称为梯度图)在作为组合模型的伴侣实现时会带来相当大的改进。此外,我们表明,它产生的“超组合”三重标记嵌入具有可解释的属性,证明有助于在所产生的三重表示进行推理。

英文摘要:

Neural models of Knowledge Base data have typically employed compositional representations of graph objects: entity and relation embeddings are systematically combined to evaluate the truth of a candidate Knowedge Base entry. Using a model inspired by Harmonic Grammar, we propose to tokenize triplet embeddings by subjecting them to a process of optimization with respect to learned well-formedness conditions on Knowledge Base triplets. The resulting model, known as Gradient Graphs, leads to sizable improvements when implemented as a companion to compositional models. Also, we show that the "supracompositional" triplet token embeddings it produces have interpretable properties that prove helpful in performing inference on the resulting triplet representations.

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。

↑