mlsanityData to 14 Oct 2026

Neural Machine Translation with Reconstruction

arXiv 1611.01874 ↗First posted 7 Nov 2016cs.CLcited by 28

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 9; 2023: 3; 2024: 5; 2025: 1.

28 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMscited by 163
  3. 2024Robustifying Safety-Aligned Large Language Models through Clean Data Curationcited by 44
  4. 2022How Large Language Models are Transforming Machine-Paraphrased Plagiarismcited by 38
  5. 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
  6. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  7. 2021Structural Information Preserving for Graph-to-Text Generationcited by 24
  8. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  9. 2022BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialogcited by 20
  10. 2022Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translationcited by 14
  11. 2021Improving Both Domain Robustness and Domain Adaptability in Machine Translationcited by 11
  12. 2021Query Rewriting via Cycle-Consistent Translation for E-Commerce Searchcited by 10
16 more
  1. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  2. 2022Understanding and Mitigating the Uncertainty in Zero-Shot Translationcited by 9
  3. 2021Sentence Concatenation Approach to Data Augmentation for Neural Machine Translationcited by 8
  4. 2022Is Encoder-Decoder Redundant for Neural Machine Translation?cited by 5
  5. 2021Data-to-text Generation by Splicing Together Nearest Neighborscited by 4
  6. 2021Modeling Coverage for Non-Autoregressive Neural Machine Translationcited by 4
  7. 2021Generating abstractive summaries of Lithuanian news articles using a transformer modelcited by 2
  8. 2022Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?cited by 2
  9. 2024WikiSplit++: Easy Data Refinement for Split and Rephrasecited by 2
  10. 2023Encoder-decoder multimodal speaker change detectioncited by 1
  11. 2023A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translationcited by 1
  12. 2024Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objectivecited by 1
  13. 2021The IWSLT 2021 BUT Speech Translation Systemscited by 0
  14. 2023An Image captioning algorithm based on the Hybrid Deep Learning Technique (CNN+GRU)cited by 0
  15. 2024Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translationcited by 0
  16. 2024NatLan: Native Language Prompting Facilitates Knowledge Elicitation Through Language Trigger Provision and Domain Trigger Retentioncited by 0