%0 Conference Proceedings %T Non-Linear Instance-Based Cross-Lingual Mapping for Non-Isomorphic Embedding Spaces %A Glavaš, Goran %A Vulić, Ivan %Y Jurafsky, Dan %Y Chai, Joyce %Y Schluter, Natalie %Y Tetreault, Joel %S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics %D 2020 %8 July %I Association for Computational Linguistics %C Online %F glavas-vulic-2020-non %X We present InstaMap, an instance-based method for learning projection-based cross-lingual word embeddings. Unlike prior work, it deviates from learning a single global linear projection. InstaMap is a non-parametric model that learns a non-linear projection by iteratively: (1) finding a globally optimal rotation of the source embedding space relying on the Kabsch algorithm, and then (2) moving each point along an instance-specific translation vector estimated from the translation vectors of the point’s nearest neighbours in the training dictionary. We report performance gains with InstaMap over four representative state-of-the-art projection-based models on bilingual lexicon induction across a set of 28 diverse language pairs. We note prominent improvements, especially for more distant language pairs (i.e., languages with non-isomorphic monolingual spaces). %R 10.18653/v1/2020.acl-main.675 %U https://aclanthology.org/2020.acl-main.675 %U https://doi.org/10.18653/v1/2020.acl-main.675 %P 7548-7555