论文标题
探索单词嵌入中语法性别的编码
An exploration of the encoding of grammatical gender in word embeddings
论文作者
论文摘要
单词的矢量表示，称为单词嵌入，在语言研究中开放了一种新的研究方法。这些表示可以捕获有关单词的不同类型的信息。名词的语法性别是基于名词的形式和语义属性的典型分类。基于单词嵌入的语法性别的研究可以深入了解如何确定语法性别。在这项研究中，我们根据确定名词的语法性别的神经分类器的准确性比较不同的单词嵌入。发现语法性别如何用瑞典语，丹麦语和荷兰语嵌入存在重叠。我们对上下文嵌入的实验结果指出，在嵌入中添加更多上下文信息对分类器的性能有害。我们还观察到，删除嵌入式培训语料库中的文章诸如文章的特征会大大降低分类性能，这表明该信息的很大一部分是在名词和文章之间的关系中编码的。
The vector representation of words, known as word embeddings, has opened a new research approach in linguistic studies. These representations can capture different types of information about words. The grammatical gender of nouns is a typical classification of nouns based on their formal and semantic properties. The study of grammatical gender based on word embeddings can give insight into discussions on how grammatical genders are determined. In this study, we compare different sets of word embeddings according to the accuracy of a neural classifier determining the grammatical gender of nouns. It is found that there is an overlap in how grammatical gender is encoded in Swedish, Danish, and Dutch embeddings. Our experimental results on the contextualized embeddings pointed out that adding more contextual information to embeddings is detrimental to the classifier's performance. We also observed that removing morpho-syntactic features such as articles from the training corpora of embeddings decreases the classification performance dramatically, indicating a large portion of the information is encoded in the relationship between nouns and articles.
