Papers by Minh-Thang Luong
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference (2021.findings-emnlp)
Copied to clipboard
Sneha Kudugunta, Yanping Huang, Ankur Bapna, Maxim Krikun, Dmitry Lepikhin, Minh-Thang Luong, Orhan Firat
| Challenge: | Sparse Mixture-of-Experts (MoE) is a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. |
| Approach: | They propose to use a task-level routing approach to extract smaller, ready-to-deploy sub-networks from large sparse models by ignoring distillation. |
| Outcome: | Experiments on WMT and a web-scale dataset show that task-level routing outperforms token-level MoE models by +1.0 BLEU on average across 30 language pairs. |
Semi-Supervised Sequence Modeling with Cross-View Training (D18-1)
Copied to clipboard
| Challenge: | Unsupervised representation learning algorithms such as word2vec and ELMo only learn from task-specific labeled data during the main training phase. |
| Approach: | They propose a semi-supervised learning algorithm that improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data. |
| Outcome: | The proposed algorithm improves the representations of a Bi-LSTM sentence encoder using a mix of labeled and unlabeled data. |
BAM! Born-Again Multi-Task Networks for Natural Language Understanding (P19-1)
Copied to clipboard
| Challenge: | Existing methods to train multi-task neural networks outperform or even match their single-task counterparts are difficult to implement. |
| Approach: | They propose a method that uses knowledge distillation to train multi-task neural networks that outperform or even match their single-task counterparts. |
| Outcome: | The proposed method outperforms or matches single-task neural networks on the GLUE benchmark. |
Enriching Biomedical Knowledge for Low-resource Language Through Large-scale Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Biomedical data and benchmarks are highly valuable but limited in low-resource languages such as English. |
| Approach: | They propose a translation model in Vietnamese that trains a pretrained Encoder-Decoder Transformer model on 20 million translated abstracts. |
| Outcome: | The proposed model can translate and produce both pretrained and supervised biomedical data in two biomedically important domains. |
STraTA: Self-Training with Task Augmentation for Better Few-shot Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in NLP demonstrate the effectiveness of applying large-scale pre-trained language models to downstream tasks. |
| Approach: | They propose a method that uses task augmentation to fine-tune unlabeled data. |
| Outcome: | The proposed approach improves sample efficiency across 12 few-shot benchmarks. |
Pre-Training Transformers as Energy-Based Cloze Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | elucidates close connection between cloze modeling and representation learning over text. |
| Approach: | They propose an energy-based cloze model for representation learning over text . they assign a scalar energy score to each input token indicating how likely it is given context . |
| Outcome: | The proposed model performs better than masked language models and faster than cloze models. |
Findings of the Third Workshop on Neural Generation and Translation (D19-56)
Copied to clipboard
Hiroaki Hayashi, Yusuke Oda, Alexandra Birch, Ioannis Konstas, Andrew Finch, Minh-Thang Luong, Graham Neubig, Katsuhito Sudoh
| Challenge: | The 3rd Workshop on Neural Machine Translation and Generation (WNGT) was held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019). |
| Approach: | They describe the results of the third workshop on Neural Generation and Translation held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019). |
| Outcome: | The results of the 3rd Workshop on Neural Machine Translation and Generation (WNGT) were summarized in Sections 3 and 4. |