Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican
Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness is correlated with amount of training data and relationships between knowledge-sharing languages. Our experiments suggest that for some languages beyond a threshold of authentic data, back-translation augmentation methods are counterproductive, while cross-lingual transfer from a sufficiently related language is preferred. We complement this finding by contributing a rule-based French-Haitian orthographic and syntactic engine and a novel method for phonological embedding. When used with multilingual techniques, orthographic transformation makes statistically significant improvements over conventional methods. And in very low-resource Jamaican MT, code-switching with a transfer language for orthographic resemblance yields a 6.63 BLEU point advantage.
Code (0)
등록된 구현이 없습니다.
Tasks
Cross-Lingual TransferMachine TranslationTransfer LearningTranslationSimilar Papers 제목 키워드 기반
Data-adaptive Transfer Learning for Low-resource Translation: A Case Study in Haitian
Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translatio…
Cross-Lingual TransferMachine TranslationTransfer LearningTranslationNeural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair
In this paper and we explore different techniques of overcoming the challenges of low-resource in Neural Machine Translation (NMT) and specifically focusing on the case of English-Marathi NMT. NMT systems require a large…
Machine TranslationNMTTransfer LearningTranslationExploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation
Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model representations can be language-agnostic, it rema…
Machine TranslationHATL: Hierarchical Adaptive-Transfer Learning Framework for Sign Language Machine Translation
Sign Language Machine Translation (SLMT) aims to bridge communication between Deaf and hearing individuals. However, its progress is constrained by scarce datasets, limited signer diversity, and large domain gaps between…
Machine TranslationTransfer LearningLearning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
Most of the Neural Machine Translation (NMT) models are based on the sequence-to-sequence (Seq2Seq) model with an encoder-decoder framework equipped with the attention mechanism. However, the conventional attention mecha…
DecoderMachine TranslationNMTTranslation