Deep learning has recently come to dominate computational linguistics, leading to claims of human-level performance in a range of language processing tasks. Like much previous computational work, deep learning–based linguistic representations adhere to the distributional meaning-in-use hypothesis, deriving semantic representations from word co-occurrence statistics. However, current deep learning methods entail fundamentally new models of lexical and compositional meaning that are ripe for theoretical analysis. Whereas traditional distributional semantics models take a bottom-up approach in which sentence meaning is characterized by explicit composition functions applied to word meanings, new approaches take a top-down approach in which sentence representations are treated as primary and representations of words and syntax are viewed as emergent. This article summarizes our current understanding of how well such representations capture lexical semantics, world knowledge, and composition. The goal is to foster increased collaboration on testing the implications of such representations as general-purpose models of semantics.

中文翻译：

---

深度学习中的语义结构

深度学习最近开始主导计算语言学，导致人们声称在一系列语言处理任务中表现出人类水平。与许多以前的计算工作一样，基于深度学习的语言表示遵循分布式使用意义假设，从单词共现统计中推导出语义表示。然而，当前的深度学习方法需要全新的词汇和组合意义模型，这些模型对于理论分析来说已经成熟。传统的分布式语义模型采用自下而上的方法，其中句子含义的特征在于应用于词义的显式组合函数，而新方法采用自上而下的方法，其中句子表示被视为主要，单词和句法的表示被视为作为涌现。本文总结了我们目前对此类表示如何很好地捕捉词汇语义、世界知识和组合的理解。目标是促进在测试此类表示的含义方面加强合作，如通用语义模型。