Multilingual NMT with a Language-Independent Attention Bridge
Explore this paper's citation graph
Summary
A new framework for the efficient development of multilingual neural machine translation (NMT) using this model and scheduled training and achieves substantial improvements over strong bilingual models and performs well for zero-shot translation, which demonstrates its ability of abstraction and transfer learning.
- Type
- preprint
- Published
- 2018-11-01
- Cited by
- 46
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W2899015110
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:53180670
Keywords
Computer science, Natural language processing, Artificial intelligence, Bridge (graph theory), Abstraction
References
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Neural Machine Translation of Rare Words with Subword Units
- Effective Approaches to Attention-based Neural Machine Translation
- Long Short-Term Memory
- 2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures
- Moses: Open Source Toolkit for Statistical Machine Translation
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- Multi-Source Neural Translation
- Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
- GloVe: Global Vectors for Word Representation
- Multi-Task Learning for Multiple Language Translation
- Multi30K: Multilingual English-German Image Descriptions
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
- OpenNMT: Open-Source Toolkit for Neural Machine Translation
- Nematus: a Toolkit for Neural Machine Translation
- Convolutional Sequence to Sequence Learning
- A Call for Clarity in Reporting BLEU Scores
- A neural interlingua for multilingual machine translation
- Are BLEU and Meaning Representation in Opposition?
- Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism
Cited by
- A Survey of Multilingual Neural Machine Translation
- An Evaluation of Language-Agnostic Inner-Attention-Based Representations in Machine Translation
- University of Tartu’s Multilingual Multi-domain WMT19 News Translation Shared Task Submission
- A Comprehensive Survey of Multilingual Neural Machine Translation
- A Brief Survey of Multilingual Neural Machine Translation.
- Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders
- Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
- Language-aware Interlingua for Multilingual Neural Machine Translation
- A Multilingual Neural Machine Translation Model for Biomedical Data
- Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
- Revisiting Modularized Multilingual NMT to Meet Industrial Demands
- Exploring Pair-Wise NMT for Indian Languages
- Multilingual Neural Machine Translation
- Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation
- Neural Machine Translation for Low-resource Languages: A Survey
- Importance-based Neuron Allocation for Multilingual Neural Machine Translation
- Learning Shared Semantic Space for Speech-to-Text Translation
- Improving Zero-shot Neural Machine Translation on Language-specific Encoders- Decoders
- Multilingual Machine Translation: Deep Analysis of Language-Specific Encoder-Decoders
- Multilingual Machine Translation with Hyper-Adapters
Related papers
- In search of abstraction: The varying abstraction model of categorization
- Two Parts of Reflective abstraction: For New Problem Solving and Mathematical Concept
- Draw Me a Flower: Processing and Grounding Abstraction in Natural Language
- The Image of Abstraction
- Modelling the Use of Abstraction in Algorithmic Problem Solving
- Cue abstraction and ideal prototype abstraction in estimation tasks