| A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models H Xu, YJ Kim, A Sharaf, HH Awadalla ICLR 2024, 2023 | 94 | 2023 |
| Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation H Xu, A Sharaf, Y Chen, W Tan, L Shen, B Van Durme, K Murray, YJ Kim ICML 2024, 2024 | 92 | 2024 |
| BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation H Xu, B Van Durme, K Murray EMNLP 2021, 2021 | 79 | 2021 |
| Gradual Fine-Tuning for Low-Resource Domain Adaptation H Xu, S Ebner, M Yarmohammadi, AS White, B Van Durme, K Murray Adapt-NLP, EACL 2021, 2021 | 46 | 2021 |
| Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction M Yarmohammadi, S Wu, M Marone, H Xu, S Ebner, G Qin, Y Chen, ... EMNLP 2021, 2021 | 34 | 2021 |
| The language barrier: Dissecting safety challenges of llms in multilingual contexts L Shen, W Tan, S Chen, Y Chen, J Zhang, H Xu, B Zheng, P Koehn, ... ACL 2024 Findings, 2024 | 33 | 2024 |
| Cross-lingual bert contextual embedding space mapping with isotropic and isometric conditions H Xu, P Koehn arXiv preprint arXiv:2107.09186, 2021 | 14 | 2021 |
| Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer H Xu, K Murray NAACL 2022 Findings, 2022 | 7 | 2022 |
| VAE based Text Style Transfer with Pivot Words Enhancement Learning H Xu, S Lu, Z Sun, C Ma, C Guo The eighteenth International Conference on Natural Language Processing, 2021 | 7 | 2021 |
| Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation H Xu, P Koehn Adapt-NLP, EACL 2021, 2021 | 6 | 2021 |
| The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains H Xu, P Koehn, K Murray EMNLP 2022, 2022 | 5 | 2022 |
| Narrowing the Gap between Zero-and Few-shot Machine Translation by Matching Styles W Tan, H Xu, L Shen, SS Li, K Murray, P Koehn, B Van Durme, Y Chen NAACL 2024 Findings, 2023 | 2 | 2023 |
| Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models T Li, H Xu, P Koehn, D Khashabi, K Murray ICLR 2024, 2023 | 2 | 2023 |
| Condensing Multilingual Knowledge with Lightweight Language-Specific Modules H Xu, W Tan, SS Li, Y Chen, B Van Durme, P Koehn, K Murray EMNLP 2023, 2023 | 2 | 2023 |
| Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity H Xu, M Elbayad, K Murray, J Maillard, V Goswami EMNLP 2023 Findings, 2023 | 2 | 2023 |
| Language-Aware Multilingual Machine Translation with Self-Supervised Learning H Xu, J Maillard, V Goswami EACL 2023 Findings, 2023 | 2 | 2023 |
| X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale H Xu, K Murray, P Koehn, H Hoang, A Eriguchi, H Khayrallah arXiv preprint arXiv:2410.03115, 2024 | 1 | 2024 |
| Streaming Sequence Transduction through Dynamic Compression W Tan, Y Chen, T Chen, G Qin, H Xu, HC Zhang, B Van Durme, P Koehn arXiv preprint arXiv:2402.01172, 2024 | 1 | 2024 |
| Adapters for Altering LLM Vocabularies: What Languages Benefit the Most? HJ Han, A Eriguchi, H Xu, H Hoang, M Carpuat, H Khayrallah arXiv preprint arXiv:2410.09644, 2024 | | 2024 |
| Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets T Li, H Xu, W Tan, K Murray, D Khashabi arXiv preprint arXiv:2410.04579, 2024 | | 2024 |
Kenton MurrayResearch Scientist, Johns HopkinsVerified email at jhu.edu
