Improving Robustness in Multilingual Machine Translation via Data Augmentation
Multilingual humans can and do seamlessly switch back and forth between languages when communicating. However, multilingual (machine) translation models are not robust to such sudden changes. In this work, we explore the robustness of multilingual MT models to language switching and propose checks to measure switching capability. We also investigate simple and effective data augmentation methods that can enhance robustness. A glass-box analysis of attention modules demonstrates the effectiveness of these methods in improving robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?
Robustness, the ability of models to maintain performance in the face of perturbations, is critical for developing reliable NLP systems. Recent studies have shown promising results in improving the robustness of models t…
Data AugmentationMachine TranslationTranslationChecks and Strategies for Enabling Code-Switched Machine Translation
Code-switching is a common phenomenon among multilingual speakers, where alternation between two or more languages occurs within the context of a single conversation. While multilingual humans can seamlessly switch back …
Data AugmentationMachine TranslationNMTTranslationPhraseOut: 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 tar…
Data AugmentationMachine TranslationNMTSentence+1SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision
Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based s…
Sign Language TranslationBenefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian
The development of machine translation (MT) has been successful in breaking the language barrier of the world’s top 10-20 languages. However, for the rest of it, delivering an acceptable translation quality is still a ch…
Machine TranslationTranslation