arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09855cs.CL
收藏

基于PMI的词嵌入中矩阵的低秩近似

Low-Rank Approximation of Matrices for PMI-based Word Embeddings

Nazarbayev University(纳扎尔巴耶夫大学)

Alena Sorokina, Aidana Karipbayeva, Zhenisbek Assylbekov

摘要:

我们进行了实证评估的几种方法的低秩近似的问题,获得基于PMI的词嵌入。所有的词向量都是在从英文维基百科(enwik9)中提取的大型语料库的一部分上训练的,该语料库被分成两个大小相等的数据集,从中获得PMI矩阵。使用重复测量设计将低秩近似(SVD、NMF、QR)方法和向量维数(250、500)分配给每个PMI矩阵重复样本。实验结果表明,与其他两种低秩近似方法相比,截断SVD方法得到的词向量在相似性和类比性两个下游任务上的性能最好。

英文摘要:

We perform an empirical evaluation of several methods of low-rank approximation in the problem of obtaining PMI-based word embeddings. All word vectors were trained on parts of a large corpus extracted from English Wikipedia (enwik9) which was divided into two equal-sized datasets, from which PMI matrices were obtained. A repeated measures design was used in assigning a method of low-rank approximation (SVD, NMF, QR) and dimensionality of the vectors (250, 500) to each of the PMI matrix replicates. Our experiments show that word vectors obtained from the truncated SVD achieve the best performance on two downstream tasks, similarity and analogy, compare to the other two low-rank approximation methods.

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。

↑