arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.04629cs.CL
收藏

主词向量

Principal Word Vectors

Ali Basirat, Christian Hardmeier, Joakim Nivre

摘要:

我们推广主成分分析嵌入到向量空间的话。概括起来主要有两个层次。第一种是将语料库的概念概括为一个计数过程,它由三个关键元素词汇集、特征(注释)集和上下文定义。这种概括使得主要的词嵌入方法能够生成关于为语料库提供的不同类型的上下文和不同类型的注释的词向量。第二个是概括大多数词嵌入方法中使用的转换步骤。为此,我们定义了两个层次的转换。第一种是二次变换,它考虑了词汇单元和上下文特征的不同类型的权重。第二种是自适应非线性变换,它重塑了数据分布,使其对主成分分析有意义。这些概括对词向量的影响本质上是关于词向量的传播和可辨别性的研究。我们还提供了一个外在的评价的贡献的主要词向量的词相似度基准和任务的依存句法分析。我们的实验最后通过比较的主要词向量和其他集的词向量与流行的词嵌入方法。从我们的内在评价指标得到的结果表明,传播和主词向量的区分度高于其他词嵌入方法。从外部评价指标获得的结果表明,主词向量优于某些词嵌入方法,并与流行的词嵌入方法相当。

英文摘要:

We generalize principal component analysis for embedding words into a vector space. The generalization is made in two major levels. The first is to generalize the concept of the corpus as a counting process which is defined by three key elements vocabulary set, feature (annotation) set, and context. This generalization enables the principal word embedding method to generate word vectors with regard to different types of contexts and different types of annotations provided for a corpus. The second is to generalize the transformation step used in most of the word embedding methods. To this end, we define two levels of transformations. The first is a quadratic transformation, which accounts for different types of weighting over the vocabulary units and contextual features. Second is an adaptive non-linear transformation, which reshapes the data distribution to be meaningful to principal component analysis. The effect of these generalizations on the word vectors is intrinsically studied with regard to the spread and the discriminability of the word vectors. We also provide an extrinsic evaluation of the contribution of the principal word vectors on a word similarity benchmark and the task of dependency parsing. Our experiments are finalized by a comparison between the principal word vectors and other sets of word vectors generated with popular word embedding methods. The results obtained from our intrinsic evaluation metrics show that the spread and the discriminability of the principal word vectors are higher than that of other word embedding methods. The results obtained from the extrinsic evaluation metrics show that the principal word vectors are better than some of the word embedding methods and on par with popular methods of word embedding.

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。

↑