arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.03520cs.LGcs.CLstat.ML
收藏

基于潜在变量模型的PMI词嵌入方法

A Latent Variable Model Approach to PMI-based Word Embeddings

Princeton University(普林斯顿大学)

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski

摘要:

语义词嵌入通过向量表示词的意义,并通过多种方法创建。许多算法在共现统计上使用非线性运算,并手动调整超参数和重新加权方法。本文提出了一种新的生成模型--动态版本的对数线性主题模型的~ \citet{mnih2007three}。方法的新颖性是使用之前计算封闭形式的表达式进行单词统计。这为PMI、word 2 vec和GloVe等非线性模型以及一些超参数选择提供了理论依据。这也有助于解释为什么低维语义嵌入包含线性代数结构,允许解决词的类比,如~ \citet{mikolov2013efficient}和许多后续论文所示。实验支持生成模型的假设,其中最重要的是,潜在的词向量是相当均匀地分散在空间中。

英文摘要:

Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper proposes a new generative model, a dynamic version of the log-linear topic model of~\citet{mnih2007three}. The methodological novelty is to use the prior to compute closed form expressions for word statistics. This provides a theoretical justification for nonlinear models like PMI, word2vec, and GloVe, as well as some hyperparameter choices. It also helps explain why low-dimensional semantic embeddings contain linear algebraic structure that allows solution of word analogies, as shown by~\citet{mikolov2013efficient} and many subsequent papers. Experimental support is provided for the generative model assumptions, the most important of which is that latent word vectors are fairly uniformly dispersed in space.

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。

↑