Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder

Abstract

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our approach does not require any special treatment on the network architecture and it allows us to learn minimal number of free parameters in a standard way of training. Our approach has shown its effectiveness in an under-resourced translation scenario with considerable improvements up to 2.6 BLEU points. In addition, the approach has achieved interesting and promising results when applied in the translation task that there is no direct parallel corpus between source and target languages.

References in corpus (1)

• ADADELTA: An Adaptive Learning Rate Method

Cited by in corpus (45)

• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
• Massively Multilingual Neural Machine Translation
• Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
• Controlling the Output Length of Neural Machine Translation
• A Comprehensive Survey of Multilingual Neural Machine Translation
• XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders
• Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning
• Trainable Greedy Decoding for Neural Machine Translation
• Neural Polysynthetic Language Modelling
• Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers
• A Study of Multilingual Neural Machine Translation
• Evaluating Multiway Multilingual NMT in the Turkic Languages
• Adapting Multilingual Neural Machine Translation to Unseen Languages
• Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
• Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
• Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering
• Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
• Multilingual End-to-End Speech Translation
• The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
• Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
• A Survey on Low-Resource Neural Machine Translation
• Multi-task Learning for Multilingual Neural Machine Translation
• Attention-based Information Fusion using Multi-Encoder-Decoder Recurrent Neural Networks
• Language Tags Matter for Zero-Shot Neural Machine Translation
• Using Monolingual Data in Neural Machine Translation: a Systematic Study
• Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation
• A Framework for Hierarchical Multilingual Machine Translation
• Improving Neural Machine Translation by Bidirectional Training
• Machine Translation with Unsupervised Length-Constraints
• EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT
• Adapting End-to-End Speech Recognition for Readable Subtitles
• Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings
• Distributionally Robust Multilingual Machine Translation
• Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021
• Learning to Learn Morphological Inflection for Resource-Poor Languages
• Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages
• Importance-based Neuron Allocation for Multilingual Neural Machine Translation
• Zero-shot Speech Translation
• Self-Learning for Zero Shot Neural Machine Translation
• Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages
• Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
• Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables