Papers by Tu Anh Dinh
Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that text-generation models can be overconfident when there are multiple correct options. |
| Approach: | They propose a QE approach called BoostedProb which boosts the model’s confidence in cases where there are multiple viable output options. |
| Outcome: | The proposed approach achieves on average +0.194 improvement in Pearson correlation to ground-truth quality and outperforms more costly approaches like supervised or ensemble-based QE in certain settings. |
End-to-End Evaluation for Low-Latency Simultaneous Speech Translation (2023.emnlp-demo)
Copied to clipboard
Christian Huber, Tu Anh Dinh, Carlos Mullov, Ngoc-Quan Pham, Thai Binh Nguyen, Fabian Retkowski, Stefan Constantin, Enes Ugan, Danni Liu, Zhaolin Li, Sai Koneru, Jan Niehues, Alexander Waibel
| Challenge: | a framework to evaluate low-latency speech translations is currently only limited to specific aspects and is not able to compare different approaches. |
| Approach: | They propose a framework to perform and evaluate low-latency speech translation in realistic conditions. |
| Outcome: | The proposed framework evaluates various aspects of low-latency speech translation under realistic conditions. |
Sigmoid Head for Quality Estimation under Language Ambiguity (2026.acl-long)
Copied to clipboard
| Challenge: | Language model (LM) probability is not reliable quality estimator, as natural language is ambiguous. |
| Approach: | They propose to train a language model (LM) probability module on top of pre-trained LMs to address these limitations. |
| Outcome: | The proposed module is an extra unembedding head with sigmoid activation to tackle the first limitation. |