保持WordNet中语义关系的密集嵌入
Dense Embeddings Preserving the Semantic Relationships in WordNet
摘要：
在本文中，我们提供了一种新的方法来生成低维向量嵌入的名词和动词的同义词集WordNet，其中的上下义关系是保留在嵌入。我们称这种嵌入为感知谱（以及用于嵌入的感知谱）。为了创建合适的标签用于语义谱的训练，我们在WordNet中设计了一种新的名词和动词同义词集的相似性度量。我们称这种相似性度量为上位词交叉相似性（HIS），因为它比较了两个同义词集之间的共同和唯一上位词。我们的实验表明，在SimLex-999数据集的名词和动词对，HIS优于WordNet中的三个相似性度量。此外，据我们所知，意义谱提供了第一个密集的同义词集嵌入，保留了WordNet中的语义关系。
英文摘要：
In this paper, we provide a novel way to generate low dimensional vector embeddings for the noun and verb synsets in WordNet, where the hypernym-hyponym relationship is preserved in the embeddings. We call this embedding the Sense Spectrum (and Sense Spectra for embeddings). In order to create suitable labels for the training of sense spectra, we designed a new similarity measurement for noun and verb synsets in WordNet. We call this similarity measurement the Hypernym Intersection Similarity (HIS), since it compares the common and unique hypernyms between two synsets. Our experiments show that on the noun and verb pairs of the SimLex-999 dataset, HIS outperforms the three similarity measurements in WordNet. Moreover, to the best of our knowledge, the sense spectra provide the first dense synset embeddings that preserve the semantic relationships in WordNet.
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。
