Litcius/Paper detail

Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation

Xin Zheng, Zhirui Zhang, Shujian Huang, Boxing Chen, Jun Xie, Weihua Luo, Jiajun Chen

202122 citationsDOIOpen Access PDF

Abstract

Recently, kNN-MT Despite being conceptually attractive, it heavily relies on high-quality indomain parallel corpora, limiting its capability on unsupervised domain adaptation, where indomain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for k-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation.

Topics & Concepts

Computer scienceMachine translationAutoencoderArtificial intelligenceTranslation (biology)Domain (mathematical analysis)Security tokenTask (project management)Representation (politics)Language modelDomain adaptationAdaptation (eye)Pattern recognition (psychology)Machine learningNatural language processingArtificial neural networkChemistryEconomicsPolitical scienceBiochemistryComputer securityClassifier (UML)LawMathematicsManagementMathematical analysisPhysicsPoliticsMessenger RNAGeneOpticsNatural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications