Pratik Jawanpuria author Satya Dev N T V author Anoop Kunchukuttan author Bamdev Mishra author 2020-jul text Association for Computational Linguistics Online conference publication 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 or concatenation of different embeddings (of a given word) is more amenable. The proposed latent space arises from two particular geometric transformations - source embedding specific orthogonal rotations and a common Mahalanobis metric scaling. Empirical results on several word similarity and word analogy benchmarks illustrate the efficacy of the proposed framework. jawanpuria-etal-2020-learning https://www.aclweb.org/anthology/2020.repl4nlp-1.6 2020-jul 39 44