# Chinese Character Decomposition for Neural MT with Multi-Word Expressions

arXiv: https://arxiv.org/abs/2104.04497 · HTML: https://mlsanity.com/paper/2104.04497/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Translationese in Machine Translation Evaluation](https://mlsanity.com/paper/1906.09833/) (2019)
- [LEPOR: An Augmented Machine Translation Evaluation Metric](https://mlsanity.com/paper/1703.08748/) (2017)
- [MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora](https://mlsanity.com/paper/2005.10583/) (2020)
- [Paying Attention to Multi-Word Expressions in Neural Machine Translation](https://mlsanity.com/paper/1710.06313/) (2017)
- [Neural Machine Translation of Logographic Languages Using Sub-character Level Information](https://mlsanity.com/paper/1809.02694/) (2018)
- [Improving Character-level Japanese-Chinese Neural Machine Translation with Radicals as an Additional Input Feature](https://mlsanity.com/paper/1805.02937/) (2018)

## Built on by (most cited first, 11 of 11)

- [Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods](https://mlsanity.com/paper/2105.03311/) (2021)
- [Measuring Uncertainty in Translation Quality Evaluation (TQE)](https://mlsanity.com/paper/2111.07699/) (2021)
- [cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE](https://mlsanity.com/paper/2108.09484/) (2021)
- [Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning](https://mlsanity.com/paper/2312.07250/) (2023)
- [CC-Riddle: A Question Answering Dataset of Chinese Character Riddles](https://mlsanity.com/paper/2206.13778/) (2022)
- [Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling](https://mlsanity.com/paper/2211.12781/) (2022)
- [An Overview on Machine Translation Evaluation](https://mlsanity.com/paper/2202.11027/) (2022)
- [Examining Large Pre-Trained Language Models for Machine Translation: What You Don't Know About It](https://mlsanity.com/paper/2209.07417/) (2022)
- [Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method](https://mlsanity.com/paper/2301.03029/) (2023)
- [HilMeMe: A Human-in-the-Loop Machine Translation Evaluation Metric Looking into Multi-Word Expressions](https://mlsanity.com/paper/2211.05201/) (2022)
- [An Empirical Study on Chinese Character Decomposition in Multiword Expression-Aware Neural Machine Translation](https://mlsanity.com/paper/2512.15556/) (2025)

## 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.