I'm a Ph.D. student at Johns Hopkins University. My research interests lie at the intersection of natural language processing and machine learning, especially in computational semantics and information extraction. My advisors are Benjamin Van Durme and Kevin Duh.

Publications

2017
Selective Decoding for Cross-lingual Open Information Extraction
Sheng Zhang, Kevin Duh and Benjamin Van Durme
To appear in IJCNLP 2017.   [ paper | bib ]
                      @InProceedings{zhang-EtAl:2017:IJCNLP,
                        author = {Zhang, Sheng and Duh, Kevin and Van Durme, Ben },
                        title     = {Selective Decoding for Cross-lingual Open Information Extraction},
                        booktitle = {Proceedings of the 8th International Joint Conference on Natural Language Processing},
                        month     = {November},
                        year      = {2017},
                        address   = {Taipei, Taiwan},
                        publisher = {Asian Federation of Natural Language Processing}
                      }
                      
An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling
Sheng Zhang, Rachel Rudinger and Benjamin Van Durme
In 12th International Conference on Computational Semantics.   [ paper | code | bib ]
                      @InProceedings{zhang-EtAl:2017:IWCS,
                        author = {Zhang, Sheng and Rudinger, Rachel and Van Durme, Ben },
                        title = {An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling},
                        booktitle = {Proceedings of the 12th International Conference on Computational Semantics (IWCS)},
                        month = {September},
                        year = {2017},
                        address = {Montpellier, France}
                      }
                      
Deep Generalized Canonical Correlation Analysis
Adrian Benton, Huda Khayrallah, Biman Gujral, Dee Ann Reisinger, Sheng Zhang and Raman Arora
arXiv preprint 2017.   [ paper | code | bib ]
                      @article{DBLP:journals/corr/BentonKGRZA17,
                        author    = {Adrian Benton and
                                     Huda Khayrallah and
                                     Biman Gujral and
                                     Drew Reisinger and
                                     Sheng Zhang and
                                     Raman Arora},
                        title     = {Deep Generalized Canonical Correlation Analysis},
                        journal   = {CoRR},
                        volume    = {abs/1702.02519},
                        year      = {2017},
                        url       = {http://arxiv.org/abs/1702.02519},
                        timestamp = {Wed, 07 Jun 2017 14:40:45 +0200},
                        biburl    = {http://dblp.uni-trier.de/rec/bib/journals/corr/BentonKGRZA17},
                        bibsource = {dblp computer science bibliography, http://dblp.org}
                      }
                      
MT/IE: Cross-lingual Open Information Extraction
with Neural Sequence-to-Sequence Models
Sheng Zhang, Kevin Duh, and Benjamin Van Durme
In EACL 2017.   [ paper | slides | code | bib ]
                      @InProceedings{zhang-duh-vandurme:2017:EACLshort,
                          author    = {Zhang, Sheng  and  Duh, Kevin  and  Van Durme, Benjamin},
                          title     = {MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models},
                          booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
                          month     = {April},
                          year      = {2017},
                          address   = {Valencia, Spain},
                          publisher = {Association for Computational Linguistics},
                          pages     = {64--70},
                          abstract  = {Cross-lingual information extraction is the task of distilling facts from
	                        foreign language (e.g. Chinese text) into representations in another language
	                        that is preferred by the user (e.g. English tuples). Conventional pipeline
	                        solutions decompose the task as machine translation followed by information
	                        extraction (or vice versa). We propose a joint solution with a neural sequence
	                        model, and show that it outperforms the pipeline in a cross-lingual open
	                        information extraction setting by 1-4 BLEU and 0.5-0.8 F1.},
                          url       = {http://www.aclweb.org/anthology/E17-2011}
                          }
                      
Ordinal Common-sense Inference
Sheng Zhang, Rachel Rudinger, Kevin Duh, and Benjamin Van Durme
To appear in TACL 2017.   [ paper | slides | corpus | samples | bib ]
                      @article{zhang-EtAl:2017:TACL,
                        author = {Zhang, Sheng and Rudinger, Rachel and Duh, Kevin and Van Durme, Ben },
                        title = {Ordinal Common-sense Inference},
                        journal = {Transactions of the Association for Computational Linguistics},
                        year = {2017}
                      }
                      
2016
Universal Decompositional Semantics on Universal Dependencies
Aaron Steven White, Drew Reisinger, Keisuke Sakaguchi, Tim Vieira, Sheng Zhang, Rachel Rudinger, Kyle Rawlins, and Benjamin Van Durme
In EMNLP 2016.   [ paper | code | bib ]
                      @InProceedings{white-EtAl:2016:EMNLP2016,
                        author    = {White, Aaron Steven  and  Reisinger, Drew  and  Sakaguchi, Keisuke  and  Vieira, Tim  and  Zhang, Sheng  and  Rudinger, Rachel  and  Rawlins, Kyle  and  Van Durme, Benjamin},
                        title     = {Universal Decompositional Semantics on Universal Dependencies},
                        booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing},
                        month     = {November},
                        year      = {2016},
                        address   = {Austin, Texas},
                        publisher = {Association for Computational Linguistics},
                        pages     = {1713--1723},
                        url       = {https://aclweb.org/anthology/D16-1177}
                        }
                      
2015
Semantic Interpretation of Superlative Expressions
via Structured Knowledge Bases
Sheng Zhang, Yansong Feng, Songfang Huang, Kun Xu, Zhe Han, and Dongyan Zhao
In ACL 2015.   [ paper | bib ]
                      @InProceedings{zhang-EtAl:2015:ACL-IJCNLP1,
                        author    = {Zhang, Sheng  and  Feng, Yansong  and  Huang, Songfang  and  Xu, Kun  and  Han, Zhe  and  Zhao, Dongyan},
                        title     = {Semantic Interpretation of Superlative Expressions via Structured Knowledge Bases},
                        booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
                        month     = {July},
                        year      = {2015},
                        address   = {Beijing, China},
                        publisher = {Association for Computational Linguistics},
                        pages     = {225--230},
                        url       = {http://www.aclweb.org/anthology/P15-2037}
                      }
                      
What Is the Longest River in the USA?
Semantic Parsing for Aggregation Questions
Kun Xu, Sheng Zhang, Yansong Feng, and Dongyan Zhao
In AAAI 2015.   [ paper | bib ]
                      @inproceedings{DBLP:conf/aaai/XuZFHZ15,
                      author    = {Kun Xu and Sheng Zhang and Yansong Feng and
                                   Songfang Huang and Dongyan Zhao},
                      title     = {What Is the Longest River in the USA? Semantic Parsing for Aggregation
                                   Questions},
                      booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference,
                                   January 25-30, 2015, Austin, Texas, {USA.}},
                      year      = {2015}
                      }
                      
2014
Answering Natural Language Questions via Phrasal Semantic Parsing
Kun Xu, Sheng Zhang, Yansong Feng, and Dongyan Zhao
In Natural Language and Processing and Chinese Computing 2014.   [ paper | bib ]
                      @incollection{xu2014answering,
                       title={Answering natural language questions via phrasal semantic parsing},
                       author={Xu, Kun and Zhang, Sheng and Feng, Yansong and Zhao, Dongyan},
                       booktitle={Natural Language Processing and Chinese Computing},
                       pages={333--344},
                       year={2014},
                       publisher={Springer}
                       }
                      

Service

Reviewer
Journal: TACL, NLE
Conference: ACL 2017, EACL 2017, IJCNLP 2017, IWCS 2017

Education

Johns Hopkins University Sep. 2015 - Present
Ph.D. in Computer Science, advised by Benjamin Van Durme and Kevin Duh
Peking University Sep. 2012 - Jul. 2015
M.S. in Computer Science, advised by Yansong Feng
Beijing University of Posts and Telecommunications Sep. 2008 - Jul. 2012
B.Eng. in Information Engineering