A5103000746- Advanced ceramic materials synthesis
- Electromagnetic wave absorption materials
- Natural Language Processing Techniques
- Advanced Antenna and Metasurface Technologies
- Topic Modeling
- Speech Recognition and Synthesis
- Advanced materials and composites
- Boron and Carbon Nanomaterials Research
- Microwave Dielectric Ceramics Synthesis
- Aluminum Alloys Composites Properties
- Speech and dialogue systems
- Metamaterials and Metasurfaces Applications
- Dielectric materials and actuators
- Intermetallics and Advanced Alloy Properties
- MXene and MAX Phase Materials
- Thermal properties of materials
- Magnesium Oxide Properties and Applications
- Electrical Contact Performance and Analysis
- Multimodal Machine Learning Applications
- Smart Materials for Construction
- Nuclear materials and radiation effects
- Music and Audio Processing
- Advanced Sensor and Energy Harvesting Materials
- Advancements in Battery Materials
- Text Readability and Simplification
Shandong University
2015-2024
China Three Gorges University
2023-2024
Central South University
2024
Third Xiangya Hospital
2024
University of South China
2024
Shandong Jianzhu University
2024
Australia and New Zealand Banking Group
2024
Institut national de recherche en informatique et en automatique
2022-2023
Inner Mongolia University
2023
Meta (United States)
2022
Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito, Ondřej Bojar, Roldano Cattoni, Anna Currey, Georgiana Dinu, Kevin Duh, Maha Elbayad, Clara Emmanuel, Yannick Estève, Marcello Federico, Christian Federmann, Souhir Gahbiche, Hongyu Gong, Roman Grundkiewicz, Barry Haddow, Benjamin Hsu, Dávid Javorský, Vĕra Kloudová, Surafel Lakew, Xutai Ma, Prashant Mathur, Paul McNamee, Kenton Murray, Maria Nǎdejde, Satoshi Nakamura, Matteo Negri, Jan Niehues, Xing Niu, John...
We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 85 languages, including several dialects or low-resource languages. do not limit extraction process alignments with English, but systematically consider all possible language pairs. In total, we are able 135M for 1620 different pairs, out which only 34M aligned English. This corpus is freely available at...
Ann Lee, Hongyu Gong, Paul-Ambroise Duquenne, Holger Schwenk, Peng-Jen Chen, Changhan Wang, Sravya Popuri, Yossi Adi, Juan Pino, Jiatao Gu, Wei-Ning Hsu. Proceedings of the 2022 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies. 2022.
Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang, Wei-Ning Hsu, Jiatao Gu, Alexei Baevski, Xian Li, Abdelrahman Mohamed, Michael Auli, Juan Pino. Proceedings of the 60th Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2022.
Peng-Jen Chen, Kevin Tran, Yilin Yang, Jingfei Du, Justine Kao, Yu-An Chung, Paden Tomasello, Paul-Ambroise Duquenne, Holger Schwenk, Hongyu Gong, Hirofumi Inaguma, Sravya Popuri, Changhan Wang, Juan Pino, Wei-Ning Hsu, Ann Lee. Findings of the Association for Computational Linguistics: ACL 2023.
Titanium diboride–boron carbide (TiB 2 –B 4 C) composite ceramics were prepared using different amounts of Ni as sintering aids by pressureless at 2100°C for 60 min under an argon atmosphere. This study focused on the effects additives densification and mechanical thermal properties TiB C ceramics. Results showed that relative density, hardness, flexural strength conductivity obtained with 1.3 wt% addition 98%, 20.4 GPa, 330 MPa 30 W/m K, respectively. However, fracture toughness was 6 m 1/2...
Paul-Ambroise Duquenne, Hongyu Gong, Ning Dong, Jingfei Du, Ann Lee, Vedanuj Goswami, Changhan Wang, Juan Pino, Benoît Sagot, Holger Schwenk. Proceedings of the 61st Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2023.
Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models enable end-to-end expressive and multilingual translations in streaming fashion. First, contribute an improved version the massively multimodal SeamlessM4T model-SeamlessM4T v2. This newer model, incorporating updated UnitY2 framework, was trained on more low-resource language...