@inproceedings{a381b1d59d1f4a34b698fd4b2fd29587,
title = "DenoisingWord Embeddings by Averaging in a Shared Space",
abstract = "We introduce a new approach for smoothing and improving the quality of word embeddings. We consider a method of fusing word embeddings that were trained on the same corpus but with different initializations. We project all the models to a shared vector space using an efficient implementation of the Generalized Procrustes Analysis (GPA) procedure, previously used in multilingual word translation. Our word representation demonstrates consistent improvements over the raw models as well as their simplistic average, on a range of tasks. As the new representations are more stable and reliable, there is a noticeable improvement in rare word evaluations.",
author = "Avi Caciularu and Ido Dagan and Jacob Goldberger",
note = "Publisher Copyright: {\textcopyright} 2021 Lexical and Computational Semantics; 10th Conference on Lexical and Computational Semantics, *SEM 2021 ; Conference date: 05-08-2021 Through 06-08-2021",
year = "2021",
doi = "10.18653/v1/2021.starsem-1.28",
language = "الإنجليزيّة",
series = "*SEM 2021 - 10th Conference on Lexical and Computational Semantics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "294--301",
editor = "Lun-Wei Ku and Vivi Nastase and Ivan Vulic",
booktitle = "*SEM 2021 - 10th Conference on Lexical and Computational Semantics, Proceedings of the Conference",
address = "الولايات المتّحدة",
}