Collaborative Regularization for Bidirectional Domain Mapping

Jen Tzung Chien, Wei Hsiang Chang

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

2 Scopus citations

Abstract

Learning both domain mapping and domain knowledge is crucial for different sequence-to-sequence (seq2seq) tasks. Traditionally, seq2seq model only characterized domain mapping while the knowledge in source and target domains was ignored. To strengthen seq2seq representation, this study presents a unified transformer for bidirectional domain mapping where collaborative regularization is imposed. This regularization enforces the bidirectional mapping constraint and avoids the model from overfitting for better generalization. Importantly, the unified learning objective is optimized for collaborative learning among different modules in two domains with two learning directions. Experiments on machine translation demonstrate the merit of unified transformer by comparing with the existing methods under different tasks and settings.

Original languageEnglish
Title of host publicationIJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780738133669
DOIs
StatePublished - 18 Jul 2021
Event2021 International Joint Conference on Neural Networks, IJCNN 2021 - Virtual, Shenzhen, China
Duration: 18 Jul 202122 Jul 2021

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2021-July

Conference

Conference2021 International Joint Conference on Neural Networks, IJCNN 2021
Country/TerritoryChina
CityVirtual, Shenzhen
Period18/07/2122/07/21

Keywords

  • domain mapping
  • machine translation
  • sequence-to-sequence learning
  • Sequential learning
  • transformer

Fingerprint

Dive into the research topics of 'Collaborative Regularization for Bidirectional Domain Mapping'. Together they form a unique fingerprint.

Cite this