猫爬需要哺乳动物移动：在成分分布语义学中保持上下义关系
Cats climb entails mammals move: preserving hyponymy in compositional distributional semantics
摘要：
为了给基于向量的意义表示更多的结构，一种方法是使用半正定（psd）矩阵。这些使我们能够对单词的相似性以及上下义关系或is-a关系进行建模。在给定的向量空间$M\otimes M^*$中，Psd矩阵可以相对容易地学习，但是要组成单词以形成短语和句子，我们需要在更大的空间中表示。在本文中，我们介绍了一种通用的方法来组成psd矩阵对应的话。我们建议将动词、形容词和其他功能词的PSD矩阵提升到与其语法类型相匹配的完全正（CP）映射。这种提升是由我们的组合规则进行的，称为压缩，压缩。与之前的合成规则（如Fuzz和Phaser）相比，KMult和BMult），Compr保持上下义关系。在数学上，Compr本身是一个CP映射，因此是线性的，一般是不可交换的。我们给出了一些建议的结构的Compr，基于蜘蛛，杯子和帽子，并产生一系列的组成规则。我们在一个小的句子蕴涵数据集上测试了这些规则，并看到了Fuzz和Phaser的性能有所改善。
英文摘要：
To give vector-based representations of meaning more structure, one approach is to use positive semidefinite (psd) matrices. These allow us to model similarity of words as well as the hyponymy or is-a relationship. Psd matrices can be learnt relatively easily in a given vector space $M\otimes M^*$, but to compose words to form phrases and sentences, we need representations in larger spaces. In this paper, we introduce a generic way of composing the psd matrices corresponding to words. We propose that psd matrices for verbs, adjectives, and other functional words be lifted to completely positive (CP) maps that match their grammatical type. This lifting is carried out by our composition rule called Compression, Compr. In contrast to previous composition rules like Fuzz and Phaser (a.k.a. KMult and BMult), Compr preserves hyponymy. Mathematically, Compr is itself a CP map, and is therefore linear and generally non-commutative. We give a number of proposals for the structure of Compr, based on spiders, cups and caps, and generate a range of composition rules. We test these rules on a small sentence entailment dataset, and see some improvements over the performance of Fuzz and Phaser.
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。
