This item is available under a Creative Commons License for non-commercial use only
1.2 COMPUTER AND INFORMATION SCIENCE, Linguistics
Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find that the distributions in the psuedo-corpora exhibit properties found in natural corpora, such as Zipf’s and Heaps’ law, and also ob- serve that the proportion of rare words in a pseudo-corpus affects the performance of its embeddings on word similarity.
Klubička, F., Maldonado, A., and Kelleher, J. (2019). Synthetic, yet natural: Properties of WordNet random walk corpora and the impact of rare words on embedding performance. InProceedings of GWC2019: 10th Global WordNet Conference, Wroclaw, Poland, 23-27 July. doi:10.21427/dkct-1z58