Yangqiu Song

I am now an assistant professor at Department of CSE at HKUST. I was an assistant professor at Lane Department of CSEE at WVU (2015-2016); a post-doc researcher at UIUC (2013-2015), a post-doc researcher at HKUST and visiting researcher at Huawei Noah's Ark Lab, Hong Kong (2012-2013); an associate researcher at Microsoft Research Asia (2010-2012); a staff researcher at IBM Research-China  (2009-2010). I received my B.E. and Ph.D. degree from Tsinghua University, China, in July 2003 and January 2009. I also worked as interns at Google in 2007-2008 and at IBM Research-China in 2006-2007.

Office: Room 3508

Clearwater Bay, Kowloon, Hong Kong

Email:  yqsong  #  cse dot ust dot hk

Research Interests: knowledge graph, text mining, information extraction, machine learning.


Full Publication List    Code   Google scholar   DBLP   Linkedin 

Call for papers: 

IEEE Transaction on Big Data Special Issue on “Knowledge Graphs: Techniques and Applications.” Submission deadline: February 28, 2017. [pdf]

Invited Talks:

IJCAI 2016 Workshop on Heterogeneous Information Network Analysis. Incorporating Structured World Knowledge into Unstructured Text via Heterogeneous Information Networks. [ppt] [pdf] (extended abstract [pdf])

ICDM 2015 Workshop on Practical Transfer Learning. Text Classification without Supervision: Incorporating World Knowledge and Domain Adaptation. [ppt] [pdf]

Teaching:

2016 Fall: COMP6211A@HKUST Topics in Text Mining and Knowledge Graph Construction, Inference, and Applications (canvas)

2016 Spring: CS472@WVU, Artificial Intelligence

2015 Fall: CS493n@WVU, Big Data Engineering

Service:

Journal Editorial Board: Journal of Artificial Intelligence Research (2016.07-2019.06)

Journal Guest Editor: IEEE Transaction on Big Data Special Issue on “Knowledge Graphs: Techniques and Applications.”

Journal Reviewer (selected): IEEE TPAMI; IEEE TKDE; IEEE TBD; IEEE SMC-B; IEEE TCybernetics; IEEE TNN; IEEE ITSTM; IEEE IS; ACM TKDD; ACM TIST; ACM TMCCA; JAIR; MLJ; DMKD; IR; PR; PRL; BMC Bioinformatics

Co-Chair: ICDM Workshop on Sentiment Elicitation from Natural Text for Information Retrieval and Extraction (SENTIRE'11)

Senior Program Committee: IJCAI'15

Program Committee: AAAI'15-17; SDM'15-17; NIPS'15-16; ICDM'14-16; ECML/PKDD'11,14-16; IJCAI'13,16; KDD'13-16; CMLA'07-15; IEEE DSAA'15; ICTAI'11-12,14-15; ACML'13-15; ICML'15; BigComp'15; CIKM'14; CIDM'13-14; COLING'14; SMIR'14; WSDM'14; IEEE-CSE'12-13; RecSys'13; LSRS'13; ACL'13; IUI'13; ParLearning'12-13; LSVA'11; OEDM'09-11; SBNMA'11

Group:

Current members:

Xin Li (PhD student, Fall 2016, B.E. Tongji)

Yan Liang (PhD student, Fall 2016, B.S. THU)

Huiru Xiao (PhD student, Fall 2016, B.S. THU)

Ziqian Zeng (PhD student, Fall 2016, B.E. SCUT, HKPF)

Ruixiang Zhang (PhD student, Fall 2016, B.E., ZJU)

Hongming Zhang (TLE MPhil student, Fall 2016, B.E. HKUST)

He Jiang (RA, 2016-2017, B.E., PKU)

Yichun Yin (RA, 2016-2017, Ph.D. candidate, PKU)

Sheng Zhou (Undergraduate Intern, 2017.02-present, HKUST)

Past students, interns, visitors, collaborators: 

Zekai J. Gao (2010.12-2011.04, ZJU->Rice), Erik Cambria (2011.03-2011.05, NTU), Xueqing Liu (2011.07-2012.03, THU->UIUC), Shusen Wang (2011.08-2012.03, ZJU->Berkeley), Wen Hua (2012.04-2012.08, RUC->UQ), Xiting Wang (2012.06-2012.11, THU), Fangzhao Wu (2012.06-2012.11, THU), Chenguang Wang (2014.08-2015.02, PKU), Wentian Zhou (2015.10-2016.05, WVU), Yiming Zhang (2016.01-2016.05, WVU)

Research Sponsors:

HK-UGC, NSFC 973 Big Data, DARPA LORELEI, Wechat WhatLab.

Recent Research Topics:

World knowledge inference and learning

1. Text classification without supervision; Learning with "flat world knowledge feature representation" and domain adaptation.

2. Classical learning problems with "structural HIN representation;" Learning with world knowledge as  indirect supervision.

Information extraction (Event extraction from news: ACE 2005, TAC KBP 2014TAC KBP 2015. Discourse parser: CoNLL Shared Task 2015)

Short text conceptualization with Web-scale concept knowledge base  (Probase: a probabilistic knowledge base about open domain concepts extracted from 1.68 billion Web documents, data download and exploration: link)

Evolutionary text clustering and topic modeling and visual analytics (TIARA : interactive text topic visualization)