mlsanityData to 14 Oct 2026

Character-based Neural Machine Translation

arXiv 1603.00810 ↗First posted 2 Mar 2016cs.CL cs.LG cs.NEcited by 33

Not on the map. Why?

Abstract (arXiv)

Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a neural MT system using character-based embeddings in combination with convolutional and highway layers to replace the standard lookup-based word representations. The resulting unlimited-vocabulary and affix-aware source word embeddings are tested in a state-of-the-art neural MT based on an attention-based bidirectional recurrent neural network. The proposed MT scheme provides improved results even when the source language is not morphologically rich. Improvements up to 3 BLEU points are obtained in the German-English WMT task.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 4; 2023: 8; 2024: 3; 2025: 6.

33 papers.

Sort:

  1. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 509
  2. 2023Tokenization and the Noiseless Channelcited by 59
  3. 2021A Survey on Green Deep Learningcited by 52
  4. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  5. 2021The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translationcited by 16
  6. 2024Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removalcited by 16
  7. 2023Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translationcited by 15
  8. 2021Alternative Input Signals Ease Transfer in Multilingual Machine Translationcited by 14
  9. 2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 14
  10. 2021Neural OCR Post-Hoc Correction of Historical Corporacited by 12
  11. 2022A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learningcited by 12
  12. 2021How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translationcited by 11
21 more
  1. 2021Lookup-Table Recurrent Language Models for Long Tail Speech Recognitioncited by 9
  2. 2022Subword-Delimited Downsampling for Better Character-Level Translationcited by 7
  3. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  4. 2021Embedding API Dependency Graph for Neural Code Generationcited by 5
  5. 2021Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Modelscited by 5
  6. 2024Frequency matters: Modeling irregular morphological patterns in Spanish with Transformerscited by 5
  7. 2024SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detectioncited by 4
  8. 2022How Effective is Byte Pair Encoding for Out-Of-Vocabulary Words in Neural Machine Translation?cited by 3
  9. 2023Neural Machine Translation for Code Generationcited by 3
  10. 2021Recurrent Neural Networks with Mixed Hierarchical Structures for Natural Language Processingcited by 2
  11. 2021Piecewise-constant Neural ODEscited by 2
  12. 2025BanglaByT5: Byte-Level Modelling for Banglacited by 2
  13. 2025Improving Language and Modality Transfer in Translation by Character-level Modelingcited by 2
  14. 2022The boundaries of meaning: a case study in neural machine translationcited by 1
  15. 2023SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translationcited by 1
  16. 2023Domain Adaptation for Arabic Machine Translation: The Case of Financial Textscited by 1
  17. 2023Larth: Dataset and Machine Translation for Etruscancited by 1
  18. 2025Self-Vocabularizing Training for Neural Machine Translationcited by 0
  19. 2025Comparative analysis of subword tokenization approaches for Indian languagescited by 0
  20. 2025A New NMT Model for Translating Clinical Texts from English to Spanishcited by 0
  21. 2025An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translationcited by 0