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 (79)

• Beyond English-Centric Multilingual Machine Translation
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Understanding Back-Translation at Scale
• A Teacher-Student Framework for Zero-Resource Neural Machine Translation
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
• Unsupervised Neural Machine Translation
• Towards a universal neural network encoder for time series
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
• An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification
• Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
• Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
• 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 Survey of Orthographic Information in Machine Translation
• Meta-Learning for Low-Resource Neural Machine Translation
• XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders
• A Comprehensive Survey of Multilingual Neural Machine Translation
• A neural interlingua for multilingual machine translation
• Low Resource Neural Machine Translation: A Benchmark for Five African Languages
• Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning
• Trainable Greedy Decoding for Neural Machine Translation
• Neural Polysynthetic Language Modelling
• Multi-Source Neural Machine Translation with Data Augmentation
• Rapid Adaptation of Neural Machine Translation to New Languages
• Multilingual Neural Machine Translation with Language Clustering
• Improving Zero-Shot Translation by Disentangling Positional Information
• Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers
• Transfer Learning in Multilingual Neural Machine Translation with Dynamic Vocabulary
• Language Graph Distillation for Low-Resource Machine Translation
• Evaluating Multiway Multilingual NMT in the Turkic Languages
• A Study of Multilingual Neural Machine Translation
• Adapting Multilingual Neural Machine Translation to Unseen Languages
• Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
• Improving Multilingual Neural Machine Translation For Low-Resource Languages: French,English - Vietnamese
• Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
• Subword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation
• Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
• Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering
• The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
• Multilingual End-to-End Speech Translation
• Cseq2seq: Cyclic Sequence-to-Sequence Learning
• Multilingual Neural Machine Translation for Zero-Resource Languages
• Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
• A Brief Survey of Multilingual Neural Machine Translation
• A Survey on Low-Resource Neural Machine Translation
• Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
• Multi-task Learning for Multilingual Neural Machine Translation
• Attention-based Information Fusion using Multi-Encoder-Decoder Recurrent Neural Networks
• Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation
• Using Monolingual Data in Neural Machine Translation: a Systematic Study
• Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
• Improving Neural Machine Translation by Bidirectional Training
• Neural Machine Translation: A Review and Survey
• A Framework for Hierarchical Multilingual Machine Translation
• Language Tags Matter for Zero-Shot Neural Machine Translation
• Machine Translation with Unsupervised Length-Constraints
• Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings
• Adapting End-to-End Speech Recognition for Readable Subtitles
• Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation
• Zero-shot Neural Transfer for Cross-lingual Entity Linking
• Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs
• EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT
• Language-Independent Representor for Neural Machine Translation
• Zero-shot Speech Translation
• Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages
• Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021
• Distributionally Robust Multilingual Machine Translation
• Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
• Improving Multilingual Translation by Representation and Gradient Regularization
• A Survey on Green Deep Learning
• Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages
• Self-Learning for Zero Shot Neural Machine Translation
• Learning to Learn Morphological Inflection for Resource-Poor Languages
• Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
• Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation
• Importance-based Neuron Allocation for Multilingual Neural Machine Translation