2000 character limit reached
Learning Geometric Word Meta-Embeddings (2004.09219v1)
Published 20 Apr 2020 in cs.CL, cs.LG, and stat.ML
Abstract: We propose a geometric framework for learning meta-embeddings of words from different embedding sources. Our framework transforms the embeddings into a common latent space, where, for example, simple averaging of different embeddings (of a given word) is more amenable. The proposed latent space arises from two particular geometric transformations - the orthogonal rotations and the Mahalanobis metric scaling. Empirical results on several word similarity and word analogy benchmarks illustrate the efficacy of the proposed framework.