Can neural machine translation do simultaneous translation?

Abstract

We investigate the potential of attention-based neural machine translation in simultaneous translation. We introduce a novel decoding algorithm, called simultaneous greedy decoding, that allows an existing neural machine translation model to begin translating before a full source sentence is received. This approach is unique from previous works on simultaneous translation in that segmentation and translation are done jointly to maximize the translation quality and that translating each segment is strongly conditioned on all the previous segments. This paper presents a first step toward building a full simultaneous translation system based on neural machine translation.

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Search-based Structured Prediction
• Tree-to-Sequence Attentional Neural Machine Translation

Cited by in corpus (28)

• Monotonic Multihead Attention
• DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting
• Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation
• End-to-End Simultaneous Speech Translation with Differentiable Segmentation
• Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learning
• Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation
• Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection
• Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
• SimulEval: An Evaluation Toolkit for Simultaneous Translation
• Simultaneous Translation Policies: From Fixed to Adaptive
• Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
• Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
• Faster Re-translation Using Non-Autoregressive Model For Simultaneous Neural Machine Translation
• Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation
• Simultaneous Neural Machine Translation with Constituent Label Prediction
• Neural Machine Translation: A Review and Survey
• Streaming Simultaneous Speech Translation with Augmented Memory Transformer
• Infusing Future Information into Monotonic Attention Through Language Models
• A Discussion on Building Practical NLP Leaderboards: The Case of Machine Translation
• BSTC: A Large-Scale Chinese-English Speech Translation Dataset
• Simultaneous Multi-Pivot Neural Machine Translation
• A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation
• Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy
• Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation
• Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers
• Full-Sentence Models Perform Better in Simultaneous Translation Using the Information Enhanced Decoding Strategy
• Stream-level Latency Evaluation for Simultaneous Machine Translation
• Narration Generation for Cartoon Videos