论文标题
基于反射的单词属性转移
Reflection-based Word Attribute Transfer
论文作者
论文摘要
通常代表像国王这样的类似关系的单词嵌入 - 可以用来改变单词的属性，包括性别。为了以这种比喻的方式将国王转移到皇后，我们根据知识是男性是男性的，减去了一个差异矢量男人。但是，对于单词和属性而言，发展此类知识非常昂贵。在这项工作中，我们提出了一种基于反射映射而没有这种类比操作的反射映射的单词属性传输的新方法。实验结果表明，我们提出的方法可以传输给定单词的单词属性，而不会更改没有目标属性的单词。
Word embeddings, which often represent such analogic relations as king - man + woman = queen, can be used to change a word's attribute, including its gender. For transferring king into queen in this analogy-based manner, we subtract a difference vector man - woman based on the knowledge that king is male. However, developing such knowledge is very costly for words and attributes. In this work, we propose a novel method for word attribute transfer based on reflection mappings without such an analogy operation. Experimental results show that our proposed method can transfer the word attributes of the given words without changing the words that do not have the target attributes.
