本周我们将迎来 PaperWeekly 的第 4 期线上 Talk，旨在帮助更多的大牛 PhD、青年学者宣传自己的工作，让更多的同学更加容易地了解到最新的研究进展。我们一直认为，单向地输出知识并不是一个最好的方式，而有效地反馈和交流可能会让知识的传播更加有意义，从而产生更大的价值。
— 关于作者 —
崔万云, a PhD candidate in the school of computer science at Fudan University, advised by Yanghua Xiao and Wei Wang. His research interests include question answering qa and knowledge graph. He has been working on QA systems at Microsoft Research Asia, Baidu (Chinese largest search engine), and Xiaoi Robot since 2012. He has published five related papers as the first author in VLDB 2017, IJCAI 2016, AAAI 2016, SIGMOD 2014, and SIGMOD 2013. He received his bachelor's degree from Fudan University in 2013.
— 演讲内容 —
Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise results, provided that natural language questions can be understood and mapped precisely to structured queries over the knowledge base. In this talk, I will introduce the KBQA project. KBQA answers questions in two ways: with question templates or with neural networks. I will also elaborate our work of adapting open domain QA systems to specific domains.
— 活动时间 —
4 月 5 日 本周三 20:00
— 直播地址 —
使用斗鱼App搜索房间号「1743775」
或
通过PC端访问：https://www.douyu.com/paperweekly
— 参与提问 —
扫描下方二维码加入本次活动的「小密圈」，圈子里的朋友可在直播过程中向主持人提交问题。本次 Talk 的作者将在演讲结束后，在线解答所有问题。如果你对本期的 Talk 感兴趣并且想和作者进行交流的话，请加入本次活动的小密圈。
活动结束后，我们还将挑选出一位最佳提问者，为其送上我们精心准备的神秘礼物：）
关于PaperWeekly
PaperWeekly 是一个分享知识和交流学问的学术组织，关注的领域是 NLP 的各个方向。如果你也经常读 paper，喜欢分享知识，喜欢和大家一起讨论和学习的话，请速速来加入我们吧。
关注微博: @PaperWeekly
微信交流群: 后台回复“加群”
