One Source, Two Targets: Challenges and Rewards of Dual Decoding
Not on the map. Why?
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.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 21 Sep 2021.
Builds on
31 of 55 references.
References · 31
- 2017Attention Is All You Needcited by 60,106
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,539
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,981
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,910
- 2018A Call for Clarity in Reporting BLEU Scorescited by 1,793
- 2016Enriching Word Vectors with Subword Informationcited by 1,581
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,487
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 786
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2016Using the Output Embedding to Improve Language Modelscited by 269
- 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
19 more
- 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
- 2016Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modelingcited by 90
- 2016Toward Multilingual Neural Machine Translation with Universal Encoder and Decodercited by 76
- 2019A Survey of Code-switched Speech and Language Processingcited by 74
- 2020SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweetscited by 62
- 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 60
- 2019Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentencescited by 55
- 2018Tied Multitask Learning for Neural Speech Translationcited by 54
- 2020Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translationcited by 54
- 2019Code-Switching for Enhancing NMT with Pre-Specified Translationcited by 53
- 2019Scheduled Sampling for Transformerscited by 46
- 2016Multi-Source Neural Translationcited by 37
- 2019Synchronous Bidirectional Neural Machine Translationcited by 27
- 2019Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Taskcited by 24
- 2018Asynchronous Bidirectional Decoding for Neural Machine Translationcited by 21
- 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
- 2019Controlling Neural Machine Translation Formality with Synthetic Supervisioncited by 18
- 2019Synchronous Bidirectional Inference for Neural Sequence Generationcited by 10
- 2021Between Flexibility and Consistency: Joint Generation of Captions and Subtitlescited by 7
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.