Revisiting adversarial autoencoder for unsupervised word translation with cycle consistency and improved training

Tasnim Mohiuddin, Shafiq Joty

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

26 Citations (Scopus)

Abstract

Adversarial training has shown impressive success in learning bilingual dictionary 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 work, we revisit 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. Extensive experimentations with European, non-European and low-resource languages show that our method is more robust and achieves better performance than recently proposed adversarial and non-adversarial approaches.

Original languageEnglish
Title of host publicationLong and Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages3857-3867
Number of pages11
ISBN (Electronic)9781950737130
Publication statusPublished - 2019
Externally publishedYes
Event2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States
Duration: 2 Jun 20197 Jun 2019

Publication series

NameNAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/TerritoryUnited States
CityMinneapolis
Period2/06/197/06/19

Fingerprint

Dive into the research topics of 'Revisiting adversarial autoencoder for unsupervised word translation with cycle consistency and improved training'. Together they form a unique fingerprint.

Cite this