通用模式嵌入的表示与推理Representation and Reasoning with Universal Schema Embeddings |
|
课程网址: | http://videolectures.net/iswc2015_mccallum_universal_schema/ |
主讲教师: | Andrew McCallum |
开课单位: | 马萨诸塞大学阿默斯特分校 |
开课时间: | 2016-01-11 |
课程语种: | 英语 |
中文简介: | 长期以来,知识表示工作一直在努力设计实体和关系类型的模式,以获得特定性和一般性之间的理想平衡,同时支持来自各种输入证据来源的推理和信息集成。在我们的知识表示“通用模式”方法中,我们对所有输入模式(从结构化知识库到OpenIE文本模式)的并集进行操作,同时通过学习向量嵌入来支持集成和泛化,向量嵌入的邻域捕获语义含义。在这次演讲中,我将简要回顾我们过去在具有通用模式关系和实体类型的知识图方面的工作,然后描述在多意义嵌入、捕捉不确定性和不对称性的高斯嵌入以及通过递归神经张量网络组合建模的多跳关系路径的新关系的逻辑含义方面的新研究。 |
课程简介: | Work in knowledge representation has long struggled to design schemas of entity- and relation-types that capture the desired balance of specificity and generality while also supporting reasoning and information integration from various sources of input evidence. In our "universal schema" approach to knowledge representation we operate on the union of all input schemas (from structured KBs to OpenIE textual patterns) while also supporting integration and generalization by learning vector embeddings whose neighbhorhoods capture semantic implicature. In this talk I will briefly review our past work on a knowledge graph with universal schema relations and entity types, then describe new research in multi-sense embeddings, Gaussian embeddings that capture uncertainty and asymmetries, and logical implicature of new relations through multi-hop relation paths compositionally modeled by recursive neural tensor networks. |
关 键 词: | 模式嵌入; 关系模型; 信息集成 |
课程来源: | 视频讲座网 |
数据采集: | 2023-07-19:chenxin01 |
最后编审: | 2023-07-19:chenxin01 |
阅读次数: | 30 |