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 1806.04523cs.CL
收藏

基于知识图谱的递归单跳预测推理

Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs

University of Pennsylvania(宾夕法尼亚大学);Microsoft Research(微软研究院);LMU Munich(慕尼黑大学)

Wenpeng Yin, Yadollah Yaghoobzadeh, Hinrich Schütze

摘要:

大规模知识图谱(KG),如Freebase,通常是不完整的。因此,多跳(mh)KG路径上的推理是问答或需要关于世界的知识的其他NLP任务所需的重要能力。mh-KG推理包括不同的场景,例如,给定一个头实体和一条关系路径,预测尾实体;或给定两个实体之间由一些关系路径连接,预测它们之间的未知关系。我们提出了ROP,循环一跳预测器,通过使用循环神经网络和实体和关系的向量表示来预测mh-KB路径的每一步的实体,具有两个好处:(i)在每一步通过训练信号更新实体和关系表示的同时对任意长度的mh路径进行建模;(ii)在统一的框架中处理不同类型的mh-KG推理。我们的模型显示了两个重要的多跳KG推理任务的最新技术:知识库完成和路径查询。

英文摘要:

Large scale knowledge graphs (KGs) such as Freebase are generally incomplete. Reasoning over multi-hop (mh) KG paths is thus an important capability that is needed for question answering or other NLP tasks that require knowledge about the world. mh-KG reasoning includes diverse scenarios, e.g., given a head entity and a relation path, predict the tail entity; or given two entities connected by some relation paths, predict the unknown relation between them. We present ROPs, recurrent one-hop predictors, that predict entities at each step of mh-KB paths by using recurrent neural networks and vector representations of entities and relations, with two benefits: (i) modeling mh-paths of arbitrary lengths while updating the entity and relation representations by the training signal at each step; (ii) handling different types of mh-KG reasoning in a unified framework. Our models show state-of-the-art for two important multi-hop KG reasoning tasks: Knowledge Base Completion and Path Query Answering.

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。

↑