I am currently a doctoral candidate at Harbin Institute of Technology, affiliated with the center for Social Computing and Information Retrieval (SCIR), supervised by Wanxiang Che, Haifeng Wang and Ting Liu. My research interests are in the areas of natural language processing, machine learning, with special interests on distributed representation learning and its applications on NLP tasks (mostly structure prediction problems). From 2014 to 2015, I am a joint Ph.D student at the Center for Language and Speech Processing (CLSP), Johns Hopkins University, supervised by David Yarowsky. Prior to that, I received my Bachelors and Masters degrees in Computer Science and Technology from Harbin Institute of Technology, Harbin, China. I received the Baidu Fellowship in 2015.
E-mail: jguo[at]ir.hit.edu.cn, jguo29[at]jhu.edu
Contact (present): Hackerman Hall 323, CLSP, Johns Hopkins University. Baltimore, MD
- Distributed representation learning for NLP (deep learning, spectral learning, clustering, etc.).
- Linguistic structure prediction (sequence modeling, parsing).
- Multilingual/Cross-lingual transfer learning and Multi-task Learning.
- Recently I am very interested in Reinforcement Learning and Interpretable Machine Learning.
- Reviewing Coordinator: ACL 2014, EMNLP 2014, NAACL 2015 - Mark Dredze (JHU) and I developed a software for Automatical Reviewer Assignment ([doc], [code]) which has been used in multiple ACL affiliated conferences.
- Secondary Reviewer: ACL 2015, IJCAI 2016
- Reviewer: EMNLP 2015, NAACL 2016, ACL 2016, NLPCC 2016, ACL 2017
- Program Committee: NAACL-2016 Workshop on Multilingual and Cross-lingual Methods in NLP
- Program Committee: ACL-2016 Student Research Workshop
- Program Committee: ACL-2017 Student Research Workshop
- 2016.09.20 Representation Learning for Multilingual Parsing. Microsoft Research Asia Ph.D. Forum 2016. Beijing, China. (Email for slides)
- 2015.10.26 Representation Learning for Cross-lingual Transfer Parsing. Carnegie Mellon University, LTI. Pittsburg, USA. (Email for slides)
- 2015.08.04 Deep Learning for Natural Language Processing. MeiTuan. Beijing, China. (Email for slides)
Projects and Achievements
- 2015: Baidu Research Fellowship (Awarded to 10 Chinese students all around the world.)
- 2014: National Graduate Scholarship
- 2014.01-2017.12: Research on Sub-Strucutre Reliability Computing of Dependency Syntactic Parsing(61370164), National Natural Science Fund (NSFC), Main Researcher.
- 2013.06-2014.01: Project: Semantic Role Labeling, with Sony Corporation.
- 2013.10: The second place of 2013 HIT's Martial Arts Competition (Tai Chi, 太极拳)
- 2013.03-2013.05: Project: Chinese Weibo Dependency Treebank Construction, with Datatang.
- 2012.06: "Outstanding Graduates of HeiLongJiang Province" Award
- 2012.01-2012.04: Project: Graph-based and Transition-based Dependency Parsing Tools, with Tencent.
- 2011.08: Outstanding Paper Award at the Annual Conference of the Computer Society of Heilongjiang Province
- 2011.06-2013.06: Language Technology Platform (LTP), one of the programmers, maintainer.
- 2010.07-2010.09: Project: Large-scale Chinese Dependency Treebank Construction. Co-PI. This corpora has been published on LDC
- 2009.06-2010.02: Open-source Project: Measure of Report Similarity. Excellent Student Innovation Project of 2009. China Innovation Program for Students (CHIPS)
- 2009.08: The third prize of 2009 National Information Security Competition, Project Leader
- 2009.04: The second prize of the American Mathematical Contest in Modeling (MCM), Team Leader
- Xiaofei Sun, Jiang Guo, Xiao Ding, Ting Liu. A General Framework for Content-enhanced Network Representation Learning. arXiv, 2016.
- Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu, Jun Xu. A Unified Architecture for Semantic Role Labeling and Relation Classification. Accepted by the 26th International Conference on Computational Linguistics (COLING). 2016.12. Osaka, Japan. [code]
- Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu. A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks. Accepted by the 26th International Conference on Computational Linguistics (COLING). 2016.12. Osaka, Japan. [code]
- Yuxuan Wang, Jiang Guo, Wanxiang Che, Ting Liu. Transition-based Chinese Semantic Dependency Graph Parsing. In Proceedings of the 15th China National Conference on Computational Linguistics (CCL), Yantai, China, 2016. (best paper award)
- Yijia Liu, Wanxiang Che, Jiang Guo, Bing Qin, Ting Liu. Exploring Segment Representations for Neural Segmentation Models. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI). 2016.07. New York City, USA. [code]
- Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu. A Distributed Representation-Based Framework for Cross-Lingual Transfer Parsing. Journal of Artificial Intelligence Research (JAIR). 2016, 55:995-1023. * This is a thoroughly extended version of the ACL-15 paper. Extensions primarily include target language adaptation with minimal supervision.
- Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu. A Representation Learning Framework for Multi-Source Transfer Parsing. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI). 2016.02. Phoenix, AZ, USA. * Data: multilingual/unified word embeddings and clusters for EN, DE, ES, FR, PT, IT, SV
- Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu. Cross-lingual Dependency Parsing Based on Distributed Representations. In Proceedings of the 53nd Annual Meeting of the Association for Computational Linguistics (ACL). 2015.07. Beijing, China. [code and data]
- Ruiji Fu*, Jiang Guo* (equal contribution), Bing Qin, Wanxiang Che, Haifeng Wang, Ting Liu. Learning Semantic Hierarchies: A Continuous Vector Space Approach. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP). 2015, 23(3):461-471.
- Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu. Revisiting Embedding Features for Simple Semi-supervised Learning. In 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014.10. Doha, Qatar. [code and data]
- Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu. Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources. In Proceedings of the 25th International Conference on Computational Linguistics (COLING). 2014.08. Dublin, Ireland.
- Ruiji Fu, Jiang Guo, Bing Qin, Wanxiang Che, Haifeng Wang, Ting Liu. Learning Semantic Hierarchies via Word Embeddings. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL). 2014.06. Baltimore, MD. [data: dev, test, readme]
- Wanxiang Che, Jiang Guo, and Ting Liu. ReliAble Dependency Arc Recognition. Expert Systems with Applications. 2014, 41(4):1716-1722.
- Jiang Guo. Confidence Measure in Dependency Parsing. Master Thesis (in Chinese). 2012. PDF | Slides.
Selected Notes and Slides
- [Note] Cross-lingual Word Representation Learning. (in Chinese)
- [Slides] Deep Q-Learning.
- [Slides] Deep Learning for NLP: A Survey.
- [Note] Recurrent Neural Network: BackPropagation Through Time.
- [Slides] Gaussian Graphical Models: Structure Estimation.
- [Slides] A Simple Tutorial on Theano.
- [Slides] Inference in Graphical Models.