Code title: "Geometry-aware domain adaptation for unsupervised alignment of word embeddings" This package contains a MATLAB implementation of the algorithm presented in the paper. P. Jawanpuria, M. Meghwanshi, and B. Mishra, "Geometry-aware domain adaptation for unsupervised alignment of word embeddings", Accepted to the Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020. The implementation is a research prototype still in development and is provided AS IS. No warranties or guarantees of any kind are given. Do not distribute this code or use it other than for your own research without permission of the authors. Feedback is greatly appreciated. Installation for MBA: ------------------------- - Set current directory as your current folder in Matlab or put it in your Matlab path. - Run "run_me_first.m" to add folders to the working path. This needs to be done at the starting of each session. - Download sample MUSE (https://github.com/facebookresearch/MUSE) en-es data in Matlab format from https://www.dropbox.com/s/353zwahfkz2hvt9/muse_data_en_es.mat?dl=1. - Copy muse_data_en_es.mat file to "tests" folder. - Run test files are provided in "tests" folder. Algorithms: ----------- - MBA: This is the main algorithm proposed in the paper. Disclaimer: ----------- - thirdpartytools/manopt is downloaded from https://manopt.org.