Haoming Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haoming Ma has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Beibei Liu
Shenyang University of Chemical Technology
3 shared publications - Fuxue Li
Yingkou Institute of Technology
3 shared publications - Hong Yan
Yingkou Institute of Technology
3 shared publications - Chuncheng Chi
Yingkou Institute of Technology
2 shared publications - Jinya Wu
Shenyang University of Chemical Technology
1 shared publication - Mingzhi Shao
Shenyang University of Chemical Technology
1 shared publication
Latest Publications
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 266-273
A Knowledge Distillation Based Translation Prompt Information Fusion Method for Neural Machine Translation
Autoregressive (AR) models represented by Transformer has attained the highest performance benchmarks in neural machine translation, which benefits from the powerful learning ability of the model with the attention mechanism. It differs from the way human translators translate a sentence, where prior knowledge plays a important role. Inspired by this, a knowledge distillation based translation prompt information fusion method is proposed to improve the AR model. It introduces two modules to improve the AR model: translation prompt information fusion and knowledge distillation. The main steps can be summarized as follows: Firstly, Training a non-autoregressive (NAR) model based on the bilingual corpus. Then, the translation prompt information generated by NAR are integrated into the AR model from two aspects. On the on hand, incorporating the translation produced by the NAR model into the decoder of the AR model. On the other hand, utilizing the output distribution of the NAR model to guide the output distribution of the AR model. Experimental results across several translation tasks with low-resource and rich-resource indicate the effectiveness of the proposed method.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 266-273
A Knowledge Distillation Based Translation Prompt Information Fusion Method for Neural Machine Translation
Autoregressive (AR) models represented by Transformer has attained the highest performance benchmarks in neural machine translation, which benefits from the powerful learning ability of the model with the attention mechanism. It differs from the way human translators translate a sentence, where prior knowledge plays a important role. Inspired by this, a knowledge distillation based translation prompt information fusion method is proposed to improve the AR model. It introduces two modules to improve the AR model: translation prompt information fusion and knowledge distillation. The main steps can be summarized as follows: Firstly, Training a non-autoregressive (NAR) model based on the bilingual corpus. Then, the translation prompt information generated by NAR are integrated into the AR model from two aspects. On the on hand, incorporating the translation produced by the NAR model into the decoder of the AR model. On the other hand, utilizing the output distribution of the NAR model to guide the output distribution of the AR model. Experimental results across several translation tasks with low-resource and rich-resource indicate the effectiveness of the proposed method.
- 22 July 2025
- Published by Springer Nature
- p. 65-76
A Word Replacement-Based Data Augmentation Method for Low-Resource Neural Machine Translation
- 22 July 2025
- Published by Springer Nature
- p. 65-76
A Word Replacement-Based Data Augmentation Method for Low-Resource Neural Machine Translation
- 24 June 2025
- Published by Springer Nature
- p. 193-206
Improving Neural Machine Translation by Multi-step Teacher-Assistant Knowledge Distillation
- 24 June 2025
- Published by Springer Nature
- p. 193-206
Improving Neural Machine Translation by Multi-step Teacher-Assistant Knowledge Distillation