@article{mohiuddin-joty-2020-unsupervised,
title = "Unsupervised Word Translation with Adversarial Autoencoder",
author = "Mohiuddin, Tasnim and
Joty, Shafiq",
journal = "Computational Linguistics",
volume = "46",
number = "2",
month = jun,
year = "2020",
url = "https://aclanthology.org/2020.cl-2.2/",
doi = "10.1162/coli_a_00374",
pages = "257--288",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohiuddin-joty-2020-unsupervised">
<titleInfo>
<title>Unsupervised Word Translation with Adversarial Autoencoder</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tasnim</namePart>
<namePart type="family">Mohiuddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">mohiuddin-joty-2020-unsupervised</identifier>
<identifier type="doi">10.1162/coli_a_00374</identifier>
<location>
<url>https://aclanthology.org/2020.cl-2.2/</url>
</location>
<part>
<date>2020-06</date>
<detail type="volume"><number>46</number></detail>
<detail type="issue"><number>2</number></detail>
<extent unit="page">
<start>257</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Unsupervised Word Translation with Adversarial Autoencoder
%A Mohiuddin, Tasnim
%A Joty, Shafiq
%J Computational Linguistics
%D 2020
%8 June
%V 46
%N 2
%F mohiuddin-joty-2020-unsupervised
%X 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.
%R 10.1162/coli_a_00374
%U https://aclanthology.org/2020.cl-2.2/
%U https://doi.org/10.1162/coli_a_00374
%P 257-288
Markdown (Informal)
[Unsupervised Word Translation with Adversarial Autoencoder](https://aclanthology.org/2020.cl-2.2/) (Mohiuddin & Joty, CL 2020)
ACL