# Asynchronous Bidirectional Decoding for Neural Machine Translation

arXiv: https://arxiv.org/abs/1801.05122 · HTML: https://mlsanity.com/paper/1801.05122/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2018.

## Built on by (most cited first, 21 of 21)

- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2112.11740/) (2021)
- [A Sequence-to-Sequence&Set Model for Text-to-Table Generation](https://mlsanity.com/paper/2306.00137/) (2023)
- [Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder](https://mlsanity.com/paper/2107.00189/) (2021)
- [Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning](https://mlsanity.com/paper/2105.14796/) (2021)
- [Exploring Dynamic Selection of Branch Expansion Orders for Code Generation](https://mlsanity.com/paper/2106.00261/) (2021)
- [Type-Driven Multi-Turn Corrections for Grammatical Error Correction](https://mlsanity.com/paper/2203.09136/) (2022)
- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)
- [Image Captioning via Compact Bidirectional Architecture](https://mlsanity.com/paper/2201.01984/) (2022)
- [Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation](https://mlsanity.com/paper/2202.13663/) (2022)
- [KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation](https://mlsanity.com/paper/2112.08266/) (2021)
- [DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder](https://mlsanity.com/paper/2203.16266/) (2022)
- [One Source, Two Targets: Challenges and Rewards of Dual Decoding](https://mlsanity.com/paper/2109.10197/) (2021)
- [Back from the future: bidirectional CTC decoding using future information in speech recognition](https://mlsanity.com/paper/2110.03326/) (2021)
- [Bidirectional Awareness Induction in Autoregressive Seq2Seq Models](https://mlsanity.com/paper/2408.13959/) (2024)
- [Enhancing the Transformer Decoder with Transition-based Syntax](https://mlsanity.com/paper/2101.12640/) (2021)
- [Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2401.00435/) (2023)
- [Spiral Language Modeling](https://mlsanity.com/paper/2112.10543/) (2021)
- [Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation](https://mlsanity.com/paper/2203.05248/) (2022)
- [A Framework for Bidirectional Decoding: Case Study in Morphological Inflection](https://mlsanity.com/paper/2305.12580/) (2023)
- [Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking](https://mlsanity.com/paper/2505.14180/) (2025)

## Abstract (arXiv)

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright manner, leaving the target-side contexts generated from right to left unexploited during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns to generate the target-side hidden state sequence from right to left. Then, the forward decoder performs translation in the forward direction, while in each translation prediction timestep, it simultaneously applies two attention models to consider the source-side and reverse target-side hidden states, respectively. With this new architecture, our model is able to fully exploit source- and target-side contexts to improve translation quality altogether. Experimental results on NIST Chinese-English and WMT English-German translation tasks demonstrate that our model achieves substantial improvements over the conventional NMT by 3.14 and 1.38 BLEU points, respectively. The source code of this work can be obtained from https://github.com/DeepLearnXMU/ABDNMT.