Wanyun Cui 崔万云
#

Email: wanyuncui1 {at} gmail.com

基本信息

  1. 复旦大学, 计算机学院博士三年级
  2. 研究兴趣:问答系统 qa demo,知识图谱 verb demo 中文同义词库

Wanyun Cui is 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 demo and knowledge graph verb demo, Chinese mention2entity . 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.


(A) Publications

  1. Wanyun Cui, Yanghua Xiao, Haixun Wang, Yangqiu Song, Seung-won Hwang, Wei Wang, KBQA: Learning Question Answering over QA Corpora and Knowledge Bases, (VLDB 2017), CCF Rank A Conference
  2. Wanyun Cui, Yanghua Xiao, Wei Wang, KBQA: An Online Template Based Question Answering System over Freebase, (IJCAI 2016), CCF Rank A Conference, demo
  3. Wanyun Cui, Xiyou Zhou, Hangyu Lin, Yanghua Xiao, Haixun Wang, Seung-won Hwang, Wei Wang, Verb Pattern: A Probabilistic Semantic Representation on Verbs, (AAAI 2016), CCF Rank A Conference PDF(info) interface
  4. Wanyun Cui, Yanghua Xiao, Haixun Wang, Wei Wang, Local Search of Communities in Large Graphs, (SIGMOD 2014), CCF Rank A Conference PDF(info)PPT(info)
  5. Wanyun Cui, Yanghua Xiao, Haixun Wang, Yiqi Lu, and Wei Wang. "Online Search of Overlapping Communities.", (SIGMOD 2013), CCF Rank A Conference PDF(info), PPT(info)
  6. Deqing Yang, Yanghua Xiao, Hanghang Tong, Wanyun Cui, Wei Wang, Towards Topic Following in Heterogeneous Information Networks, (ASONAM 2015)
  7. Hui Wang, Wanyun Cui, Yanghua Xiao, Hanghang Tong, Robust Network Construction against Intentional Attack, (BigComp 2015), Invited Paper
  8. Yaoliang Chen, Ji Hong, Wanyun Cui, Jacques Zaneveld, Wei Wang, Richard Gibbs, Yanghua Xiao and Rui Chen, CGAP-align: A High Performance DNA Short Read Alignment Tool, Plos One, 2013, 8(4): e61033, SCI, IF=4 PDF(info)
  9. Yanghua xiao, Ji Hong, Wanyun Cui, Zhenying He, Wei Wang, Guodong Feng, Branch Code: An Efficient Labeling Scheme for Query Answering on Trees, IEEE 28th International Conference on Data Engineering(ICDE 2012) CCF Rank A Conference.

(B) 主要项目经历
问答系统:
  1. KBQA: 作为主要负责人 基于知识图谱和问答语料的自然语言问答系统,在QALD-3上正确率76%,超过所有同类系统。News 已经支持中文问答。
  2. 小度机器人: 负责实体类答案深度问答技术,百度深度问答项目,在一站到底数据集上准确率从81%提升到85%。
  3. 小i机器人: 负责问答系统架构重构,小i机器人公司项目,将其问答技术核心从传统文本挖掘信息检索,向知识图谱和深度学习方向引导。
其它:
  1. 中文同义词库: 作为主要负责人提供368万中文实体-别称的高质量实体同义词库。利用开放的互联网数据及深度学习模型。
  2. 人人猎头钢铁侠&复旦生涯: 作为主要负责人对简历和职位做语义理解和智能匹配。从百万级别简历/职位数据中在1秒内实现高精确度的匹配。应用于人人猎头APP和复旦生涯微信号。
  3. 两会舆情分析: 负责13年两会微博热点词汇分析,工作被新民晚报及解放日报报导。
  4. AffineSWOptimization: 作为主要负责人 使用CPU级的SSE2技术加速Smith-Waterman算法,在Topcoder的marathon match中排名第八。
(B) Projects
Question Answering Systems:
  1. KBQA: Main Contributor Project in Microsoft Research Asia. A QA system over knowledge bases. Its precision on QALD-3 is 76%, which beats other state-of-the-art competitors. News Supporting Chinese QA now.
  2. Deep QA: in charge of factoid question answering Project in Baidu Inc. (Chinese largest search engine company) The precision increases from 81% to 85% on the Chinese YiZhanDaoDi dataset.
  3. Xiaoi Robot: in charge of qa system reconstruction Project in Xiaoi Robot Inc. Reconstructing its qa system framework from traditional information retrieval techniques to deep learning and knowledge graph techniques.
Other Projects:
  1. Chinese mention2entity: Main Contributor Providing 3.68 million mention2entity facts from web knowledge extraction and deep learning.
  2. Iron Man Project in Shanghai Zhongpin Inc. & Fudan Career Project in Fudan Univeersity: Main Contributor Rank and sort millions of resume descriptions and job descriptions with nlp techniques.
  3. Public Sentiment Analysis for the Chinese National Sessions: in charge of hot keyword analysis The result has been published in two Chinese well-known newspapers: Xinmin Evening News, and Liberation Daily.
  4. AffineSWOptimization: Main Contributor Using CPU leveled instructions, SSE2, to accelerate the Smith-Waterman algorithm. Rank 8th in the Topcoder marathon match.


(C) 实习经历

  1. 2014.7-2014.11 百度深度问答项目(小度机器人),实体类答案问答技术
  2. 2013.4-2013.6: 上海众聘信息科技有限公司,简历-职位的匹配度计算
  3. 2012.1-2012.11:微软亚洲研究院,构建基于大型知识库的问答系统。

(C) Experiences:

  1. Jul 2014 - Nov 2014: Deep QA project, Baidu Inc. (Chinese largest search engine company)
  2. Apr 2013 - Jun 2013: Shanghai Zhongpin Inc. Working on computing resume-job relatedness.
  3. Jan 2012 - Nov 2012: Microsoft Research Asia, working on the construction of QA system over large scale knowledgebase, with Dr. Haixun Wang


(D) 所获奖项

  1. 2017 复旦大学研究生学术之星 复旦博士生最高学术荣誉
  2. 2016 复旦大学博士优秀毕业生
  3. 2016 EMC优秀奖学金
  4. 2014 "微软学者"奖学金提名奖
  5. 2014 复旦大学董氏奖学金
  6. 2013 复旦大学毕业生之星,复旦毕业生最高荣誉,每年仅有十位学生获得
  7. 2013 光华自立奖学金学术科研奖(理科),复旦由学生评选的最高奖项
  8. 2013 SIGMOD Student Travel Award
  9. 2013 上海市优秀毕业生
  10. 2013 勒卡斯杯数据挖掘竞赛 第二名
  11. 2012 谷歌优秀学生奖学金,为了表彰杰出学术贡献
  12. 2011,2009 ACM/ICPC 北京/上海赛区邀请赛 两获金牌
  13. 2009 百度之星程序设计竞赛决赛 (全国前50)
(D) Awards
  1. 2016 EMC outstanding scholarship
  2. 2014 Microsoft Fellowship Nomination
  3. 2013 Fudan Outstanding Undergraduate Award top honor for Fudan undergraduates. 10 students win this award each year.
  4. 2013 Guanghua Self-Reliance Scholarship for Academic (science), top student-organized scholarship in Fudan University
  5. 2013 SIGMOD Student Travel Award
  6. 2013 Shanghai Outstanding Graduate Award
  7. 2013 second place in LECAST data mining competition
  8. 2012 Google Excellence Scholarship, for having demonstrated superior academic achievement
  9. 2011, 2009 ACM/ICPC Beijing/Shanghai Region Invitation Contest double gold medals
  10. 2009 BAIDU ASTAR Programming Contest Top 50

(E) Talks
  1. 2014.7.25 <Community Search: a Lightweight Way to Reveal the Community Structure> ,邀请报告,“大数据连接未来——2014腾讯博士、博士后大数据论坛”,北京
  2. 2016.7.9 <知识库上的问答系统:实体、文本及系统观> ,邀请报告,“携程深度学习Meetup”,上海
  3. 2016.10.20 <基于知识图谱的问答系统:实体、文本、系统,以及领域适配>,邀请报告,“2016中国计算机大会,科学大数据及其应用博士生论坛”,太原
  4. 2017.3.22 <Question Answering over Knowledge Bases>,邀请报告,上海财经大学信息管理与工程学院,上海
  5. 2017.4.5 <基于知识库的问答>,邀请报告,PaperWeekly线上Talk,斗鱼平台

添加新附件

只有授权的用户才能上传新附件。
« 该页面(修订版 )最后由 shawyh 在 02-五月-2017 11:24 修改。