# One Source, Two Targets: Challenges and Rewards of Dual Decoding

arXiv: https://arxiv.org/abs/2109.10197 · HTML: https://mlsanity.com/paper/2109.10197/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 21 Sep 2021.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)
- [Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling](https://mlsanity.com/paper/1611.01462/) (2016)
- [Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder](https://mlsanity.com/paper/1611.04798/) (2016)
- [A Survey of Code-switched Speech and Language Processing](https://mlsanity.com/paper/1904.00784/) (2019)
- [SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets](https://mlsanity.com/paper/2008.04277/) (2020)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences](https://mlsanity.com/paper/1909.08582/) (2019)
- [Tied Multitask Learning for Neural Speech Translation](https://mlsanity.com/paper/1802.06655/) (2018)
- [Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation](https://mlsanity.com/paper/2011.00747/) (2020)
- [Code-Switching for Enhancing NMT with Pre-Specified Translation](https://mlsanity.com/paper/1904.09107/) (2019)
- [Scheduled Sampling for Transformers](https://mlsanity.com/paper/1906.07651/) (2019)
- [Multi-Source Neural Translation](https://mlsanity.com/paper/1601.00710/) (2016)
- [Synchronous Bidirectional Neural Machine Translation](https://mlsanity.com/paper/1905.04847/) (2019)
- [Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task](https://mlsanity.com/paper/1906.04138/) (2019)
- [Asynchronous Bidirectional Decoding for Neural Machine Translation](https://mlsanity.com/paper/1801.05122/) (2018)
- [Can You Traducir This? Machine Translation for Code-Switched Input](https://mlsanity.com/paper/2105.04846/) (2021)
- [Controlling Neural Machine Translation Formality with Synthetic Supervision](https://mlsanity.com/paper/1911.08706/) (2019)
- [Synchronous Bidirectional Inference for Neural Sequence Generation](https://mlsanity.com/paper/1902.08955/) (2019)

## Built on by (most cited first, 2 of 2)

- [Joint Generation of Captions and Subtitles with Dual Decoding](https://mlsanity.com/paper/2205.06522/) (2022)
- [A Framework for Bidirectional Decoding: Case Study in Morphological Inflection](https://mlsanity.com/paper/2305.12580/) (2023)

## Abstract (arXiv)

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text. We present an analysis of possible implementations of dual decoding, and experiment with four applications. Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.