在线报告:ZOOM会议号-679 459 3439
报 告 人: Ihab Ilyas教授
主 持 人: 邹磊教授
【报告摘要】
In this talk I present Saga, an end-to-end platform for incremental and continuous construction of large scale knowledge graphs. Saga demonstrates the complexity of building such platform in industrial settings with strong consistency, latency, and coverage requirements. In the talk, I discuss challenges around the following: building source adapters for ingesting heterogenous data sources; building entity linking and fusion pipelines for constructing coherent knowledge graphs that adhere to a common controlled vocabulary; updating the knowledge graphs with real-time streams; and finally, exposing the constructed knowledge via a variety of services. Graph services include: low-latency query answering; graph analytics; ML-biased entity disambiguation and semantic annotation; and other graph-embedding services to power multiple downstream applications. Saga is used in production at large scale to power a variety of user-facing knowledge features.
![](https://oss-emcsprod-public.modb.pro/image/auto/modb_20230113_48fc0f1c-92e5-11ed-a6e1-38f9d3cd240d.png)
欢迎关注北京大学王选计算机研究所数据管理实验室微信公众号“图谱学苑“
实验室官网:https://mod.wict.pku.edu.cn/
微信社区群:请回复“社区”获取
gStore官网:http://www.gstore.cn/
GitHub:https://github.com/pkumod/gStore
Gitee:https://gitee.com/PKUMOD/gStore
![](https://oss-emcsprod-public.modb.pro/image/auto/modb_20230113_49295242-92e5-11ed-a6e1-38f9d3cd240d.png)
![](https://oss-emcsprod-public.modb.pro/image/auto/modb_20230113_4935dd28-92e5-11ed-a6e1-38f9d3cd240d.png)