Papers by Shaomu Tan
How Far can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data (2024.findings-acl)
Copied to clipboard
| Challenge: | a common solution to zero-shot translation is to add as many related translation directions as possible to the training corpus. |
| Approach: | They show that a small amount of multi-parallel data can achieve significant zero-shot improvements . they say that the resulting non-English performance is close to the complete translation upper bound . |
| Outcome: | The proposed model achieves +21.7 ChrF++ non-English translation improvements on EC30 dataset . the resulting non- English performance exceeds M2M100 by an average of 5.9 ChrF+ . |
Towards a Better Understanding of Variations in Zero-Shot Neural Machine Translation Performance (2023.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has investigated causes of poor zero-shot performance, but new study suggests it does not exhibit poor zero shot capability. |
| Approach: | They propose to investigate the presence of significant variations in zero-shot performance . target-side translation quality is most influential factor, with vocabulary overlap impacting zero- shot capabilities . |
| Outcome: | The results show that the target side translation quality is the most influential factor . linguistic properties, such as language family and writing system, play a role . |
ReMedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Regression-based neural metrics struggle with inconsistency of human ratings . prompting large language models (LLMs) for MT scoring has also shown promise . |
| Approach: | They propose a MT metric framework that reformulates translation evaluation as a reward modeling task. |
| Outcome: | The proposed framework surpasses larger WMT winners and massive closed LLMs across 39 language pairs and 111 MT systems. |
Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent MT metrics like xCOMET, Met-ricX, and Remedy have strong correlations with human preferences, but they are black boxes, revealing little insight into why a translation is good or bad. |
| Approach: | They propose a reasoning-driven generative MT metric trained with reinforcement learning from pairwise translation preferences without requiring error-span annotations or distillation from closed LLMs. |
| Outcome: | The proposed reasoning-driven generative MT metric produces step-by-step analyses of accuracy, fluency, and completeness, enabling more interpretable assessments. |
Neuron Specialization: Leveraging Intrinsic Task Modularity for Multilingual Machine Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Language-specific modeling methods that focus on heuristics for allocation of capacity and lack knowledge transfer capabilities are often prone to interference due to conflicting optimization demands. |
| Approach: | They propose a method that identifies specialized neurons to modularize feed-forward layers and updates them through sparse networks to avoid interference under multilingual translation. |
| Outcome: | The proposed approach achieves consistent performance gains over strong baselines with additional analyses showing reduced interference and increased knowledge transfer. |
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation (2026.acl-long)
Copied to clipboard
Shaomu Tan, Dawei Zhu, Ke Tran, Michael Denkowski, Sony Trenous, Leonardo F. R. Ribeiro, Bill Byrne, Felix Hieber
| Challenge: | Large language models (LLMs) have made document-level machine translation increasingly practical, enabled by long-context modeling and strong generation quality. |
| Approach: | They propose to use document-level MT followed by segment-level refinement to find the strongest and most stable improvements across six LLMs and seven language pairs. |
| Outcome: | The proposed method outperforms error-specific prompting and evaluate-then-refine schemes in document-level translation. |