Please use this identifier to cite or link to this item:
|Title:||Unsupervised word translation with adversarial autoencoder||Authors:||Mohiuddin, Tasnim
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2020||Source:||Mohiuddin, T. & Joty, S. (2020). Unsupervised word translation with adversarial autoencoder. Computational Linguistics, 46(2), 257-288. https://dx.doi.org/10.1162/COLI_a_00374||Journal:||Computational Linguistics||Abstract:||Crosslingual word embeddings learned from monolingual embeddings have a crucial role in many downstream tasks, ranging from machine translation to transfer learning. Adversarial training has shown impressive success in learning crosslingual embeddings and the associated word translation task without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this article, we investigate adversarial autoencoder for unsupervised word translation and propose two novel extensions to it that yield more stable training and improved results. Our method includes regularization terms to enforce cycle consistency and input reconstruction, and puts the target encoders as an adversary against the corresponding discriminator. We use two types of refinement procedures sequentially after obtaining the trained encoders and mappings from the adversarial training, namely, refinement with Procrustes solution and refinement with symmetric re-weighting. Extensive experimentations with high- and low-resource languages from two different data sets show that our method achieves better performance than existing adversarial and non-adversarial approaches and is also competitive with the supervised system. Along with performing comprehensive ablation studies to understand the contribution of different components of our adversarial model, we also conduct a thorough analysis of the refinement procedures to understand their effects.||URI:||https://hdl.handle.net/10356/148677||ISSN:||0891-2017||DOI:||10.1162/COLI_a_00374||Rights:||© 2020 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits you to copy and redistribute in any medium or format, for non-commercial use only, provided that the original work is not remixed, transformed, or built upon, and that appropriate credit to the original source is given. For a full description of the license, please visit https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Jan 20, 2022
Updated on Jan 20, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.