论文标题
关于$ \ ell_2 $ sense嵌入规范的好奇情况
On the Curious Case of $\ell_2$ norm of Sense Embeddings
论文作者
论文摘要
我们表明，静态感嵌入的$ \ ell_2 $规范编码用于学习感官嵌入的训练语料库中的频率相关的信息。这一发现可以看作是以前已知的与嵌入嵌入有关的词嵌入的关系的扩展。我们的实验结果表明，尽管它很简单，但$ \ ell_2 $ sense嵌入规范对于多个单词相关的任务，例如（a）最常见的感觉预测，（b）context（wic）（wic）和（c）sense sense disamemiguation（wsd）是一个令人惊讶的有效功能。特别是，通过简单地将有意义嵌入的$ \ ell_2 $标准作为分类器中的功能，我们表明我们可以改善使用静态嵌入式的WIC和WSD方法。
We show that the $\ell_2$ norm of a static sense embedding encodes information related to the frequency of that sense in the training corpus used to learn the sense embeddings. This finding can be seen as an extension of a previously known relationship for word embeddings to sense embeddings. Our experimental results show that, in spite of its simplicity, the $\ell_2$ norm of sense embeddings is a surprisingly effective feature for several word sense related tasks such as (a) most frequent sense prediction, (b) Word-in-Context (WiC), and (c) Word Sense Disambiguation (WSD). In particular, by simply including the $\ell_2$ norm of a sense embedding as a feature in a classifier, we show that we can improve WiC and WSD methods that use static sense embeddings.
