Research talk: Domain-specific pretraining for vertical search
185
Microsoft Research329 тыс
Следующее
25.01.22 – 1712:08Популярные
22.09.23 – 8971:11:02
Опубликовано 25 января 2022, 1:37
Speaker: Tristan Naumann, Principal Researcher, Microsoft Research
Information overload is a prevalent challenge in many high-value domains. Search in biomedicine, and many other vertical domains, is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. In this talk, we discuss work that presents a general approach for vertical search based on domain-specific pretraining and present a case study in the biomedical domain, Microsoft Biomedical Search.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Information overload is a prevalent challenge in many high-value domains. Search in biomedicine, and many other vertical domains, is challenging due to the scarcity of direct supervision from click logs. Self-supervised learning has emerged as a promising direction to overcome the annotation bottleneck. In this talk, we discuss work that presents a general approach for vertical search based on domain-specific pretraining and present a case study in the biomedical domain, Microsoft Biomedical Search.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Свежие видео
4 дня – 3 6081:43
8 дней – 2 0250:45
12 дней – 11 4200:25
Случайные видео
05.06.23 – 96 7327:25
27.04.23 – 36 3160:55
16.04.23 – 4 5942:12
10.12.20 – 315 49716:05
31.08.19 – 8010:51
3 дня – 21 80111:34
1 день – 1 4030:46
2 дня – 4 2700:31
3 дня – 5740:41
8 дней – 59510:56
22 часа – 26032:29