A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well
Machine Learning
2020-03-04 v2 Computation and Language
Machine Learning
Abstract
In this paper, we reproduce the experiments of Artetxe et al. (2018b) regarding the robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. We show that the reproduction of their method is indeed feasible with some minor assumptions. We further investigate the robustness of their model by introducing four new languages that are less similar to English than the ones proposed by the original paper. In order to assess the stability of their model, we also conduct a grid search over sensible hyperparameters. We then propose key recommendations applicable to any research project in order to deliver fully reproducible research.
Keywords
Cite
@article{arxiv.1912.01706,
title = {A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well},
author = {Nicolas Garneau and Mathieu Godbout and David Beauchemin and Audrey Durand and Luc Lamontagne},
journal= {arXiv preprint arXiv:1912.01706},
year = {2020}
}
Comments
Accept in REPROLANG@LREC2020