On metric embedding for boosting semantic similarity computations

Julien Subercaze (1) , Christophe Gravier (1) , Frédérique Laforest (1)

1 LHC - Laboratoire Hubert Curien

Computing pairwise word semantic similarity is widely used and serves as a building block in many tasks in NLP. In this paper, we explore the embedding of the shortest-path metrics from a knowledge base (Wordnet) into the Hamming hyper-cube, in order to enhance the computation performance. We show that, although an isometric embedding is untractable, it is possible to achieve good non-isometric embeddings. We report a speedup of three orders of magnitude for the task of computing Leacock and Chodorow (LCH) similarity while keeping strong correlations (r = .819, ρ = .826).

Domaines: Base de données [cs.DB]; Informatique et langage [cs.CL]

Julien Subercaze, Christophe Gravier, Frédérique Laforest. On metric embedding for boosting semantic similarity computations. Association of Computational Linguistics, Jul 2015, Beijing, China. ⟨hal-01166163⟩