# Neural Machine Translation with Reconstruction

arXiv: https://arxiv.org/abs/1611.01874 · HTML: https://mlsanity.com/paper/1611.01874/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2016.

## Built on by (most cited first, 28 of 28)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs](https://mlsanity.com/paper/2501.18585/) (2025)
- [Robustifying Safety-Aligned Large Language Models through Clean Data Curation](https://mlsanity.com/paper/2405.19358/) (2024)
- [How Large Language Models are Transforming Machine-Paraphrased Plagiarism](https://mlsanity.com/paper/2210.03568/) (2022)
- [Prevent the Language Model from being Overconfident in Neural Machine Translation](https://mlsanity.com/paper/2105.11098/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks](https://mlsanity.com/paper/2105.00573/) (2021)
- [BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2205.02471/) (2022)
- [Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation](https://mlsanity.com/paper/2203.08442/) (2022)
- [Improving Both Domain Robustness and Domain Adaptability in Machine Translation](https://mlsanity.com/paper/2112.08288/) (2021)
- [Query Rewriting via Cycle-Consistent Translation for E-Commerce Search](https://mlsanity.com/paper/2103.00800/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Understanding and Mitigating the Uncertainty in Zero-Shot Translation](https://mlsanity.com/paper/2205.10068/) (2022)
- [Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2104.08478/) (2021)
- [Is Encoder-Decoder Redundant for Neural Machine Translation?](https://mlsanity.com/paper/2210.11807/) (2022)
- [Data-to-text Generation by Splicing Together Nearest Neighbors](https://mlsanity.com/paper/2101.08248/) (2021)
- [Modeling Coverage for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2104.11897/) (2021)
- [Generating abstractive summaries of Lithuanian news articles using a transformer model](https://mlsanity.com/paper/2105.03279/) (2021)
- [Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?](https://mlsanity.com/paper/2211.13865/) (2022)
- [WikiSplit++: Easy Data Refinement for Split and Rephrase](https://mlsanity.com/paper/2404.09002/) (2024)
- [Encoder-decoder multimodal speaker change detection](https://mlsanity.com/paper/2306.00680/) (2023)
- [A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation](https://mlsanity.com/paper/2308.06063/) (2023)
- [Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective](https://mlsanity.com/paper/2405.18922/) (2024)
- [The IWSLT 2021 BUT Speech Translation Systems](https://mlsanity.com/paper/2107.06155/) (2021)
- [An Image captioning algorithm based on the Hybrid Deep Learning Technique (CNN+GRU)](https://mlsanity.com/paper/2301.02440/) (2023)
- [Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation](https://mlsanity.com/paper/2406.11632/) (2024)
- [NatLan: Native Language Prompting Facilitates Knowledge Elicitation Through Language Trigger Provision and Domain Trigger Retention](https://mlsanity.com/paper/2408.03544/) (2024)

## Abstract (arXiv)

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that NMT tends to repeatedly translate some source words while mistakenly ignoring other words. To alleviate this problem, we propose a novel encoder-decoder-reconstructor framework for NMT. The reconstructor, incorporated into the NMT model, manages to reconstruct the input source sentence from the hidden layer of the output target sentence, to ensure that the information in the source side is transformed to the target side as much as possible. Experiments show that the proposed framework significantly improves the adequacy of NMT output and achieves superior translation result over state-of-the-art NMT and statistical MT systems.