Progress in Computational Semantics: Structured Distributions and their Applications(4)

第三届自然语言处理与中文计算会议(NLPCC 2014)——Over the past few years, many NLP researchers have turned toward Distributional Semantics models and Deep Learning to overcome problems that traditional propositional models of semantics simply cannot handle.Distributional Semantics (DS) assumes that much of the semantics of a word can be captured by a distribution of words associated with it and represented as a vector. Deep learning methods such as Recursive Neural Nets are one way to perform composition that seems to work.Dr. Hovy postulate that decomposing the vector into a tensor, by representing separately the distributions of words associated with specific relations off the target word, provides additional representational power.

关键词: 计算语义学 结构化布线 深度学习 语义分析和结构化语言模型

主讲人:Prof. Eduard Hovy 机构:Carnegie Mellon University

时长:0:11:57 年代:2014年