Haibin Liu, PhD

Last updated: November 6, 2012.                    Download my CV

Contact Information

Email: haibin.liu@nih.gov           Phone: (720) 341-1888         Address: Bethesda, MD 20894

Research Interests

Natural Language Processing (NLP)   Graph-based pattern learning    Text Mining in biomedical literature

Web Usage and Content Mining    Graph Kernel-based machine learning    Semi-supervised Learning

Selected Publications (See CV for complete publications)

Haibin Liu, Vlado Keselj, and Christian Blouin, "Biological Event Extraction using Subgraph Matching," Computational Intelligence, in press.

Ravikumar Komandur, Haibin Liu, Judith Cohn, Michael E. Wall and Karin Verspoor, "Literature Mining of Protein-Residue Associations with Graph Rules Learned through Distant Supervision," Journal of Biomedical Semantics, 3(Suppl 3):S2, 2012.

Haibin Liu, Vlado Keselj, Christian Blouin and Karin Verspoor, "Subgraph Matching-based Literature Mining for Biomedical Relations and Events," In Proceedings of AAAI 2012 Fall Symposium on Information Retrieval and Knowledge Discovery in Biomedical Text, Arlington, VA, USA, November 2012.

Haibin Liu, Tom Christiansen, William A Baumgartner Jr, and Karin Verspoor, "BioLemmatizer: a lemmatization tool for morphological processing of biomedical text," Journal of Biomedical Semantics, 3:3, 2012.

Ravikumar Komandur, Haibin Liu, Judith Cohn, Michael E. Wall and Karin Verspoor, "Pattern Learning Through Distant Supervision for Extraction of Protein-Residue Associations in the Biomedical Literature," In Proceedings of the Tenth International Conference on Machine Learning and Applications (ICMLA), Honolulu, Hawaii, USA, December 2011.

Haibin Liu, Ravikumar Komandur, and Karin Verspoor, "From Graphs to Events: A Subgraph Matching Approach for Information Extraction from Biomedical Text," In Proceedings of BioNLP Shared Task 2011 Workshop, Portland, Oregon, USA, June 2011.

Haibin Liu, Christian Blouin, and Vlado Keselj, "Biological Event Extraction using Subgraph Matching," In Proceedings of SMBM´10, Fourth International Symposium on Semantic Mining in Biomedicine, Hinxton, Cambridgeshire, UK, October 2010.

Haibin Liu, Christian Blouin, and Vlado Keselj, "Sentence Identification of Biological Interactions using Patricia Tree Generated Patterns and Genetic Algorithm Optimized Parameters," Elsevier Science Publishers Data & Knowledge Engineering, vol.69, no.1, pp.137-152, 2010.

Vlado Keselj, Haibin Liu, Norbert Zeh, Christian Blouin, and Chris Whidden, "Finding Optimal Parameters for Edit Distance Based Sequence Classification is NP-Hard," In Proceedings of StReBio´09, KDD-09 Workshop on Statistical Relational Mining and Learning in Bioinformatics, Paris, France, June 2009.

Haibin Liu, Christian Blouin, and Vlado Keselj, "Identifying Interaction Sentences from Biological Literature Using Automatically Extracted Patterns," In Proceedings of BioNLP 2009, NAACL/HLT 2009 Workshop, Boulder, Colorado, USA, June 2009.

Haibin Liu, Christian Blouin, and Vlado Keselj, "An Unsupervised Method for Extracting Domain-specific Affixes in Biological Literature," In Proceedings of BioNLP 2007, ACL 2007 Workshop, Prague, Czech Republic, June 2007.

Haibin Liu, and Vlado Keselj, "Combined Mining of Web Server Logs and Web Contents for Classifying User Navigation Patterns and Predicting Users´ Future Requests," Data & Knowledge Engineering, vol.61, no.2, pp.304-330, May 2007. (Published on-line in 2006).

Lei Shi, Haibin Liu, Xiaojing Yang, Zuying Gao, Yujie Dong, and Zuoyi Zhang, "A Personal Computer-Based Simulation-and-Control-Integrated Platform for 10-MW High-Temperature Gas-Cooled Reactor," Nuclear Technology, American Nuclear Society (ANS), vol.145, no.2, pp.189-203, Feb. 2004.

Work Experience

Oct. 2012 - Present

Staff Scientist, NCBI/NLM/NIH, USA

Working on building semi-supervised learning systems for knowledge extraction from biomedical literature

Developing graph kernels used in conjunction with SVMs for literature mining of biological relations and events

Supervisor: Dr. John Wilbur

Jan. 2011 - Sep. 2012

Postdoctoral Researcher, Hunter Lab, University of Colorado School of Medicine, USA

Designed an Approximate Subgraph Matching (ASM) algorithm and integrated it into our graph-based event extraction system to extract complex relational knowledge in the literature

Worked on the collaboration with Pfizer/Selventa to extract statements of biological events from biomedical literature, represented in Biological Expression Language (BEL)

Supervisors: Dr. Karin Verspoor and Dr. Larry Hunter

Sep. 2005 - Nov. 2010

Research Assistant, Faculty of Computer Science, Dalhousie University, Canada

Research work on biomedical Natural Language Processing with a focus on information extraction from biomedical literature

Supervisors: Dr. Christian Blouin and Dr. Vlado Keselj

May 2009 - Aug. 2009

Supervisor, Faculty of Computer Science, Dalhousie University, Canada

Co-supervise Allan Lavell, an NSERC Undergraduate Summer Research Award winner, with Dr. Christian Blouin on his summer intern project of the topic "Using MetaMap to annotate biomedical terms in the GENIA Corpus"

Sep.2006 - May 2007

Intern, MITACS Inc. and Kanayo Software Inc.

Worked on the project "A Practical Method for Extracting Prefixes and Suffixes of Biological Terms"

Jan. 2006 - Jan. 2008

Teaching Assistant, Faculty of Computer Science, Dalhousie University, Canada

"Data and Knowledge Fundamentals" instructed by Dr. Qigang Gao

"Principles of Programming Languages" instructed by Dr. Vlado Keselj

"Databases and Data Mining for Health Informatics" instructed by Dr. Vlado Keselj

"Databases, Data Warehouses and Data Mining for Electronic Commerce" instructed by Dr. Vlado Keselj

Sep. 2004 - Aug. 2005

Research Assistant, Faculty of Computer Science, Dalhousie University, Canada

Investigated whether associating a content mining approach with regular web usage mining could result in a more accurate classification of user navigation patterns, and consequently lead to a more accurate prediction of users´ future requests.

Supervisor: Dr. Vlado Keselj

Sep. 2002 - Jul. 2003

Intern & Research Assistant, Reactor Theory Division of the Institute of Nuclear Energy Technology (INET), Tsinghua University, China

Independently established a unified standard for simulation systems of High-Temperature Gas-Cooled Reactors based on the knowledge of Human Engineering and nuclear component designs

Improved on the graphical man-machine interface of the original Simulation-and-Control-Integrated Platform of 10-MV High-Temperature Gas-Cooled Reactor (HTR-10); Expanded the original single-computer-based system into an abbreviated-intranet-based one

Supervisors: Dr. Lei Shi and Dr. Zhiwei Zhou

Jul. 2000 - Aug. 2001

Management Consultant & Programmer, Analysis Department, Ever Bright International Trade Company, China

Investigated chemical products on the international market and the procedures of importing and exporting

Developed a business management system

Feb. 2000 - Jul. 2000

Research Assistant, School of Materials Science and Engineering, Beijing University of Chemical Technology, China

Compared the thermal-oxidation stability between PVC copolymerization and pure PVC

Supervisor: Professor Meizhen Zhang

Education

Sep. 2005 - Nov. 2010

Ph.D. in Computer Science, Dalhousie University, Canada

Sep. 2003 - Jul.2005

Master of Electronic Commerce, Dalhousie University, Canada

Sep. 2001 - Jul. 2003

Bachelor of Science in Computer Science and Technology, Tsinghua University, China

Sep. 1996 - Jul. 2000

Bachelor of Engineering in Chemical Engineering, Beijing University of Chemical Technology, China

Professional Skills

Programming

Perl, Java, C/C++, Python, JSP, JavaScript, JUnit, WEKA, JUNG library, MPI, GPU

Database

Microsoft SQL Server, MySQL, Access

Operating system

Mac OS, Windows, Linux/Unix OS

Software

ESM

an exact subgraph matching (ESM) algorithm for dependency graphs

BioLemmatizer

a lemmatization tool for morphological processing of biomedical text

Awards

2012

BioLemmatizer Research Paper Featured as Editor's Pick

2011 - 2012

NLM Informatics Training Grant 5T15LM009451

2004 - 2010

Faculty of Graduate Studies Scholarship, Dalhousie University

2001

Excellent Employee, Ever Bright International Trade Company

1997 - 2000

Outstanding Student Fellowship, Beijing University of Chemical Technology