mlsanityData to 7 Oct 2026

Chinese Character Decomposition for Neural MT with Multi-Word Expressions

arXiv 2104.04497 ↗First posted 9 Apr 2021cs.CL cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Chinese character decomposition has been used as a feature to enhance Machine Translation (MT) models, combining radicals into character and word level models. Recent work has investigated ideograph or stroke level embedding. However, questions remain about different decomposition levels of Chinese character representations, radical and strokes, best suited for MT. To investigate the impact of Chinese decomposition embedding in detail, i.e., radical, stroke, and intermediate levels, and how well these decompositions represent the meaning of the original character sequences, we carry out analysis with both automated and human evaluation of MT. Furthermore, we investigate if the combination of decomposed Multiword Expressions (MWEs) can enhance the model learning. MWE integration into MT has seen more than a decade of exploration. However, decomposed MWEs has not previously been explored.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 11 of its 34 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

11 of 34 references.

References · 11

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  4. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  5. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  6. 2019Translationese in Machine Translation Evaluationcited by 38
  7. 2017LEPOR: An Augmented Machine Translation Evaluation Metriccited by 6
  8. 2020MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corporacited by 6
  9. 2017Paying Attention to Multi-Word Expressions in Neural Machine Translationcited by 5
  10. 2018Neural Machine Translation of Logographic Languages Using Sub-character Level Informationcited by 4
  11. 2018Improving Character-level Japanese-Chinese Neural Machine Translation with Radicals as an Additional Input Featurecited by 2

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 5; 2023: 2; 2024: 0; 2025: 1.

11 papers.

  1. 2021Translation Quality Assessment: A Brief Survey on Manual and Automatic Methodscited by 23
  2. 2021Measuring Uncertainty in Translation Quality Evaluation (TQE)cited by 16
  3. 2021cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSEcited by 8
  4. 2023Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learningcited by 8
  5. 2022CC-Riddle: A Question Answering Dataset of Chinese Character Riddlescited by 6
  6. 2022Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modelingcited by 6
  7. 2022An Overview on Machine Translation Evaluationcited by 4
  8. 2022Examining Large Pre-Trained Language Models for Machine Translation: What You Don't Know About Itcited by 3
  9. 2023Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Methodcited by 2
  10. 2022HilMeMe: A Human-in-the-Loop Machine Translation Evaluation Metric Looking into Multi-Word Expressionscited by 0
  11. 2025An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translationcited by 0