Abstract:

摘要：

Since modern word embeddings are motivated by a distributional hypothesis and are, therefore, based on local co-occurrences of words, it is only to be expected that synonyms and antonyms can have very similar embeddings.

由于现代单词嵌入是由分布假设驱动的，并且它们基于单词上的局部共现，因此同义词和反义词的词嵌入非常相似，这是意料之中的。

Contrary to this widespread assumption, this paper shows that modern embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors.

与这种普遍的假设相反，本文表明了，尽管相应的向量之间的余弦相似度很小，但现代嵌入包含区分同义词和反义词之间的信息。

This information is encoded in the geometry of the embeddings and could be extracted with a manifold learning procedure or {\em contrasting map}.

该信息被编码在嵌入的几何图形中，并且可以用流形学习过程或{\em对比图}提取。

Such a map is trained on a small labeled subset of the data and can produce new empeddings that explicitly highlight specific semantic attributes of the word.

这种映射被训练用在数据的一个小的打上标记的子集上，并且它可以产生明确突出单词的特定语义属性的新嵌入。

The new embeddings produced by the map are shown to improve the performance on downstream tasks.

显示了由映射产生的新嵌入，以提高下游任务的性能。