Chuncheng Chi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chuncheng Chi has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Hong Yan
Yingkou Institute of Technology
16 shared publications - Fuxue Li
Yingkou Institute of Technology
15 shared publications - Peijun Xie
Yingkou Institute of Technology
10 shared publications - Beibei Liu
Shenyang University of Chemical Technology
4 shared publications - Zhen Zhang
Yingkou Institute of Technology
3 shared publications - Haoming Ma
Shenyang University of Chemical Technology
2 shared publications
Latest Publications
- 17 July 2026
- Published by Springer Nature
- p. 90-101
A Low-Resource Neural Machine Translation Data Augmentation Method Based on Keyword Exchange
- 17 July 2026
- Published by Springer Nature
- p. 90-101
A Low-Resource Neural Machine Translation Data Augmentation Method Based on Keyword Exchange
- 15 July 2026
- Published by Springer Nature
- p. 354-365
Relation-Aware Gated Visual Modulation for Robust Multimodal Knowledge Graph Embedding
- 15 July 2026
- Published by Springer Nature
- p. 354-365
Relation-Aware Gated Visual Modulation for Robust Multimodal Knowledge Graph Embedding
- 15 July 2026
- Published by Springer Nature
- p. 366-377
Commonsense Violations in Multimodal Large Language Models: A Knowledge-Guided Analysis
- 15 July 2026
- Published by Springer Nature
- p. 366-377
Commonsense Violations in Multimodal Large Language Models: A Knowledge-Guided Analysis
- Open Access
- 12 February 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (2) , e0342772
Dependency-aware self-attention for robust neural machine translation
Neural machine translation (NMT) has significantly benefited from integrating various forms of contextual information. However, conventional Transformer-based translation models primarily rely on self-attention mechanisms that are inherently position-invariant, making them inadequate for effectively capturing explicit syntactic dependencies, especially in low-resource scenarios or morphologically rich languages. To address this limitation, we propose a Dependency-Aware Self-Attention (DASA) mechanism that explicitly incorporates syntactic dependency structures into the attention computation. Our method first leverages a dependency parser to derive syntactic trees from source sentences, generating a dependency distance matrix representing pairwise syntactic proximity. This matrix is transformed into a normalized syntactic bias, which is seamlessly integrated into the attention mechanism through element-wise modulation of attention logits. By doing so, DASA guides attention weights towards syntactically relevant tokens, enhancing the Transformer encoder’s structural awareness and representation quality. Experimental results demonstrate that our approach substantially improves the translation performance, particularly in settings with limited training data. Experiments show that DASA enhances syntactic awareness and robustness, especially under data scarcity.
- 12 February 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (2) , e0342772
Open AccessDependency-aware self-attention for robust neural machine translation
Neural machine translation (NMT) has significantly benefited from integrating various forms of contextual information. However, conventional Transformer-based translation models primarily rely on self-attention mechanisms that are inherently position-invariant, making them inadequate for effectively capturing explicit syntactic dependencies, especially in low-resource scenarios or morphologically rich languages. To address this limitation, we propose a Dependency-Aware Self-Attention (DASA) mechanism that explicitly incorporates syntactic dependency structures into the attention computation. Our method first leverages a dependency parser to derive syntactic trees from source sentences, generating a dependency distance matrix representing pairwise syntactic proximity. This matrix is transformed into a normalized syntactic bias, which is seamlessly integrated into the attention mechanism through element-wise modulation of attention logits. By doing so, DASA guides attention weights towards syntactically relevant tokens, enhancing the Transformer encoder’s structural awareness and representation quality. Experimental results demonstrate that our approach substantially improves the translation performance, particularly in settings with limited training data. Experiments show that DASA enhances syntactic awareness and robustness, especially under data scarcity.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-258
A Keyword Exchange-Based Data Augmentation Method for Low-Resource Neural Machine Translation
Recent advancements in Transformer-based architectures have established new benchmarks in neural machine translation (NMT), though their efficacy remains constrained by the availability of large-scale parallel corpora. This limitation becomes particularly pronounced for low-resource language pairs, where the scarcity of bilingual training data often leads to suboptimal translation performance. To address this challenge, we introduce Keyword Exchange (KE), a novel data augmentation framework designed to enhance translation quality in data-scarce scenarios. The proposed methodology operates through a three-stage pipeline: (1) A selective filtering approach is first applied to identify and retain high-quality sentence pairs from both source and target language corpora; (2) The KE algorithm is then deployed on the filtered target-side sentences, strategically substituting keywords to generate syntactically valid yet semantically divergent pseudo-monolingual data; (3) Finally, an Alignment Mixture strategy synthesizes these augmented monolingual fragments with their corresponding source-side counterparts, producing a robust pseudo-parallel corpus that significantly expands the effective training set. Empirical validation across multiple low-resource translation benchmarks demonstrates the framework's superiority over conventional baselines. Notably, our approach achieves a maximum BLEU score improvement of 0.74 points compared to a strong Transformer-based baseline, outperforming several state-of-the-art data augmentation techniques.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-258
A Keyword Exchange-Based Data Augmentation Method for Low-Resource Neural Machine Translation
Recent advancements in Transformer-based architectures have established new benchmarks in neural machine translation (NMT), though their efficacy remains constrained by the availability of large-scale parallel corpora. This limitation becomes particularly pronounced for low-resource language pairs, where the scarcity of bilingual training data often leads to suboptimal translation performance. To address this challenge, we introduce Keyword Exchange (KE), a novel data augmentation framework designed to enhance translation quality in data-scarce scenarios. The proposed methodology operates through a three-stage pipeline: (1) A selective filtering approach is first applied to identify and retain high-quality sentence pairs from both source and target language corpora; (2) The KE algorithm is then deployed on the filtered target-side sentences, strategically substituting keywords to generate syntactically valid yet semantically divergent pseudo-monolingual data; (3) Finally, an Alignment Mixture strategy synthesizes these augmented monolingual fragments with their corresponding source-side counterparts, producing a robust pseudo-parallel corpus that significantly expands the effective training set. Empirical validation across multiple low-resource translation benchmarks demonstrates the framework's superiority over conventional baselines. Notably, our approach achieves a maximum BLEU score improvement of 0.74 points compared to a strong Transformer-based baseline, outperforming several state-of-the-art data augmentation techniques.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 259-265
Incorporating Word Translations Into Neural Machine Translation
Transformer-based Neural Machine Translation (NMT) models have attained state-of-the-art performance within the machine translation community, automatically acquiring translation knowledge from bilingual corpora through the attention mechanism. This contrasts with the approach of human translators, who heavily rely on prior knowledge during sentence translation. Inspired by this disparity, we propose a Word Translation Augmentation (WTA) method to enhance Transformer-based NMT models. Our methodology comprises three key steps: initially, we construct word alignment rules based on the training set; subsequently, we generate translation rules for source words in accordance with these alignment rules; finally, we integrate potential translation candidates for each source word into the NMT model during both training and testing phases. Additionally, the WTA method introduces the concept of Mixup for augmenting translation candidates of source words and employs two augmentation strategies to enrich the encoder. Experimental results on the WMT14 (German $\leftrightarrow$ English) and AIChallenger 2018 (Chinese $\leftrightarrow$ English) translation tasks demonstrate the effectiveness of our proposed method compared to strong baseline models.- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 259-265
Incorporating Word Translations Into Neural Machine Translation
Transformer-based Neural Machine Translation (NMT) models have attained state-of-the-art performance within the machine translation community, automatically acquiring translation knowledge from bilingual corpora through the attention mechanism. This contrasts with the approach of human translators, who heavily rely on prior knowledge during sentence translation. Inspired by this disparity, we propose a Word Translation Augmentation (WTA) method to enhance Transformer-based NMT models. Our methodology comprises three key steps: initially, we construct word alignment rules based on the training set; subsequently, we generate translation rules for source words in accordance with these alignment rules; finally, we integrate potential translation candidates for each source word into the NMT model during both training and testing phases. Additionally, the WTA method introduces the concept of Mixup for augmenting translation candidates of source words and employs two augmentation strategies to enrich the encoder. Experimental results on the WMT14 (German $\leftrightarrow$ English) and AIChallenger 2018 (Chinese $\leftrightarrow$ English) translation tasks demonstrate the effectiveness of our proposed method compared to strong baseline models.- 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.
- 25 July 2025
- Published by Springer Nature
- p. 29-40
A Source Template-Based Data Augmentation Method for Low-Resource Neural Machine Translation
- 25 July 2025
- Published by Springer Nature
- p. 29-40
A Source Template-Based Data Augmentation Method for Low-Resource Neural Machine Translation
- 25 July 2025
- Published by Springer Nature
- p. 209-220
Improving Low-Resource Neural Machine Translation with Dependency Distance-Based Self-Attention
- 25 July 2025
- Published by Springer Nature
- p. 209-220
Improving Low-Resource Neural Machine Translation with Dependency Distance-Based Self-Attention
- 25 July 2025
- Published by Springer Nature
- p. 113-124
Sentence Trunk Fusion for Neural Machine Translation
- 25 July 2025
- Published by Springer Nature
- p. 113-124
Sentence Trunk Fusion for Neural Machine Translation