PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation
Data Augmentation methods for Neural Machine Translation (NMT) such as back- translation (BT) and self-training (ST) are quite popular. In a multilingual NMT system, simply copying monolingual source sentences to the target (Copying) is an effective data augmentation method. Back-translation aug- ments parallel data by translating monolingual sentences in the target side to source language. In this work we propose to use a partial back- translation method in a multilingual setting. Instead of translating the entire monolingual target sentence back into the source language, we replace selected high confidence phrases only and keep the rest of the words in the target language itself. (We call this method PhraseOut). Our experiments on low resource multilingual translation models show that PhraseOut gives reasonable improvements over the existing data augmentation methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMachine TranslationNMTSentenceTranslationSimilar Papers 제목 키워드 기반
Training Data Augmentation for Code-Mixed Translation
Machine translation of user-generated code-mixed inputs to English is of crucial importance in applications like web search and targeted advertising. We address the scarcity of parallel training data for training such mo…
Data AugmentationMachine TranslationTranslationLeveraging Language Identification to Enhance Code-Mixed Text Classification
The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especially English with a regional language, on s…
ClassificationHate Speech DetectionLanguage IdentificationSentence+3Enabling Code-Mixed Translation: Parallel Corpus Creation and MT Augmentation Approach
Code-mixing, use of two or more languages in a single sentence, is ubiquitous; generated by multi-lingual speakers across the world. The phenomenon presents itself prominently in social media discourse. Consequently, the…
Machine TranslationSentenceTranslationImproved Mixed-Example Data Augmentation
In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training exa…
Data AugmentationImage AugmentationAdversarial synthesis based data-augmentation for code-switched spoken language identification
Spoken Language Identification (LID) is an important sub-task of Automatic Speech Recognition(ASR) that is used to classify the language(s) in an audio segment. Automatic LID plays an useful role in multilingual countrie…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationGenerative Adversarial Network+4