arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.00751cs.CL
收藏

评估面向多层级词汇语义的分布式表征:一项研究计划

Evaluating Distributed Representations for Multi-Level Lexical Semantics: A Research Proposal

Tsinghua University(清华大学)

Zhu Liu

AI总结:

该研究计划提出形式化局部、全局、混合三层词汇语义,并通过多语言数据集、多种语言模型与语言分析理论,系统评估神经网络分布式表征编码词汇意义的能力。

摘要:

在海量原始句子数据上训练的现代神经网络(NNs),通过将单个词压缩为稠密、连续、高维向量来构建分布式表征。这些表征被期望能够捕捉多层级的词汇意义。在本论文中,我们的目标是检验神经网络的分布式表征在编码词汇意义方面的效能。首先,我们识别并形式化词汇语义的三个层级:local(局部)、global(全局)和 mixed(混合)层级。随后,针对每一层级,我们通过收集或构建多语言数据集、利用多种语言模型并采用语言分析理论来评估语言模型。本论文在计算模型与词汇语义之间架起桥梁,旨在使二者相互补充。

英文摘要:

Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture multi-level lexical meaning. In this thesis, our objective is to examine the efficacy of distributed representations from NNs in encoding lexical meaning. Initially, we identify and formalize three levels of lexical semantics: \textit{local}, \textit{global}, and \textit{mixed} levels. Then, for each level, we evaluate language models by collecting or constructing multilingual datasets, leveraging various language models, and employing linguistic analysis theories. This thesis builds a bridge between computational models and lexical semantics, aiming to complement each other.

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。

↑