Dense Embeddings Preserving the Semantic Relationships in WordNet
This work addresses the need for dense embeddings that capture semantic hierarchies in lexical resources like WordNet, which is incremental as it builds on existing embedding methods but focuses on preserving specific relationships.
The paper tackles the problem of generating low-dimensional vector embeddings for WordNet synsets that preserve hypernym-hyponym relationships, introducing Sense Spectra and a new similarity measurement called Hypernym Intersection Similarity (HIS), which outperforms existing WordNet similarity measurements on the SimLex-999 dataset.
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.