arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.09620cs.CL
收藏

基于语义子空间分析的高效句子嵌入

Efficient Sentence Embedding via Semantic Subspace Analysis

Univ. of Southern California(南加州大学);Signal and Image Processing Institute Department of Electrical and Computer Engineering University of Southern California(南加州大学电气工程与计算机科学系信号与图像处理研究所);University of Southern California(南加州大学)

Bin Wang, Fenxiao Chen, Yuncheng Wang, C. -C. Jay Kuo

摘要:

本文提出了一种基于语义子空间分析的句子嵌入方法--语义子空间句子嵌入(S3 E)。鉴于词嵌入可以捕捉语义关系,而语义相似的词往往形成语义组在一个高维的嵌入空间,我们开发了一个句子表示方案,通过分析其组成词的语义子空间。具体来说,我们从两个方面构建了一个句子模型。首先,我们使用组内描述符来表示位于同一语义组中的单词。其次,我们用组间描述符刻画了多个语义组之间的交互。所提出的S3 E方法在文本相似性任务和监督任务上进行了评估。实验结果表明,它提供了相当或更好的性能比国家的最先进的。我们的S3 E方法的复杂性也远远低于其他参数化模型。

英文摘要:

A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embeddings can capture semantic relationship while semantically similar words tend to form semantic groups in a high-dimensional embedding space, we develop a sentence representation scheme by analyzing semantic subspaces of its constituent words. Specifically, we construct a sentence model from two aspects. First, we represent words that lie in the same semantic group using the intra-group descriptor. Second, we characterize the interaction between multiple semantic groups with the inter-group descriptor. The proposed S3E method is evaluated on both textual similarity tasks and supervised tasks. Experimental results show that it offers comparable or better performance than the state-of-the-art. The complexity of our S3E method is also much lower than other parameterized models.

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。

↑