枪支和老虎是危险的，厨房里的鸭子和斑马不是：测试词嵌入是否可以告诉
Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell
摘要：
本文提出了一种研究词嵌入获取的语义信息的性质的方法。我们提出了一种方法，扩展现有的人类引发的语义属性数据集与黄金负面的例子，使用人群的判断。我们的实验方法测试了监督分类器识别词嵌入向量中语义特征的能力，并将其与基于全向量余弦相似性的特征识别方法进行了比较。这种方法背后的思想是，由分类器识别的属性，但不是通过完整的向量比较，被嵌入捕获。两种方法都不能识别的属性则不能识别。我们的研究结果提供了一个初步的迹象表明，语义属性相关的实体交互的方式（例如危险）被捕获，而感知信息（例如颜色）不表示。我们的结论是，虽然是初步的，这些结果表明，我们的方法是适合于识别哪些属性被嵌入捕获。
英文摘要：
This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and com- pares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.
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。
