ニュース&特集
Efficiently and effectively scaling up language model pretraining for best language representation model on GLUE and SuperGLUE
| Jianfeng Gao と Saurabh Tiwary
As part of Microsoft AI at Scale (opens …
SOLOIST: Pairing transfer learning and machine teaching to advance task bots at scale
| Baolin Peng, Chunyuan Li, Jinchao Li, Lars Liden, と Jianfeng Gao
The increasing use of personal assistant…
The science behind semantic search: How AI from Bing is powering Azure Cognitive Search
| Rangan Majumder, Alec Berntson, Daxin Jiang (姜大昕), Jianfeng Gao, Furu Wei, と Nan Duan
Azure Cognitive Search (opens in new tab…
HEXA: Self-supervised pretraining with hard examples improves visual representations
| Chunyuan Li, Lei Zhang, と Jianfeng Gao
Humans perceive the world through observ…
VinVL: Advancing the state of the art for vision-language models
| Pengchuan Zhang, Lei Zhang, と Jianfeng Gao
Humans understand the world by perceivin…
Microsoft DeBERTa surpasses human performance on the SuperGLUE benchmark
| Pengcheng He, Xiaodong Liu, Jianfeng Gao, と Weizhu Chen
Natural language understanding (NLU) is …
Domain-specific language model pretraining for biomedical natural language processing
| Hoifung Poon と Jianfeng Gao
COVID-19 highlights a perennial problem …
ニュース | VentureBeat
Microsoft researchers claim ‘state-of-the-art’ biomedical NLP model
In a paper (opens in new tab) published …
Objects are the secret key to revealing the world between vision and language
| Chunyuan Li, Lei Zhang, と Jianfeng Gao
Humans perceive the world through many c…