文本分类中的双曲质心计算
Hyperbolic Centroid Calculations for Text Classification
摘要:
NLP的一个新发展是双曲词嵌入的构造。与欧几里德映射相反,双曲嵌入不是由向量表示,而是由双曲空间中的点表示。这使得构建文档表示的最常见的基本方案,即词向量的平均值,在双曲线设置中毫无意义。我们重新解释的矢量平均值的矢量所代表的点的质心,并研究各种双曲线质心计划和它们的有效性在文本分类。
英文摘要:
A new development in NLP is the construction of hyperbolic word embeddings. As opposed to their Euclidean counterparts, hyperbolic embeddings are represented not by vectors, but by points in hyperbolic space. This makes the most common basic scheme for constructing document representations, namely the averaging of word vectors, meaningless in the hyperbolic setting. We reinterpret the vector mean as the centroid of the points represented by the vectors, and investigate various hyperbolic centroid schemes and their effectiveness at text classification.
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。