Xiaochang Peng
Xiaochang Peng 


Graduate Student
Department of Computer Science
University of Rochester
Rochester, NY 14627

Office:627, Computer Studies Building
E-mail: xpeng@cs.rochester.edu

Biography

I am a 5th year PhD student at the Computer Science Department of University of Rochester. My advisor is Prof. Daniel Gildea. My research interests are machine learning and statistical methods towards machine translation and semantic parsing. My current research mainly focuses on machine learning approaches for mapping natural language strings to semantic graph representations. I got my Bachelar's degree from Peking University in China. I also have two years' research intern experience in the NLP group at Institute of Computer Science & Technology of Peking University

Publication

  1. AMR-to-text Generation with Synchronous Node Replacement Grammar. Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang and Daniel Gildea. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL-17)
  2. Addressing the Data Sparsity Issue in Neural AMR Parsing. Xiaochang Peng*, Chuan Wang*, Daniel Gildea and Nianwen Xue. European Chapter of the Association for Computational Linguistics (EACL-17), Valencia, Spain, 2017. (*: equal contribution)
  3. AMR-to-text Generation as a Traveling Salesman Problem. Linfeng Song, Yue Zhang, Xiaochang Peng, Zhiguo Wang and Daniel Gildea. In Conference on Empirical Methods in Natural Language Processing (EMNLP-16), 2016.
  4. Exploring phrase-compositionality in skip-gram models. Xiaochang Peng and Daniel Gildea. Arxiv
  5. UofR at SemEval-2016 Task 8: Learning Synchronous Hyperedge Replacement Grammar for AMR Parsing. Xiaochang Peng and Daniel Gildea. NAACL-HLT 2016 Workshop on Semantic Evaluation (SemEval-2016)
  6. A Synchronous Hyperedge Replacement Grammar based approach for AMR parsing. Xiaochang Peng, Linfeng Song and Daniel Gildea. The SIGNLL Conference on Computational Natural Language Learning (CoNLL), Beijing, China, 2015.
  7. Type-based MCMC for Sampling Tree Fragments from Forests. Xiaochang Peng and Daniel Gildea. Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 2014.
  8. Capturing Long-distance Dependencies in Sequence Models: A Case Study of Chinese Part-of-speech Tagging. Weiwei Sun, Xiaochang Peng and Xiaojun Wan. International Joint Conference on Natural Language Processing (IJCNLP), 2013.

Teaching Assistant

  1. 2016 Spring

    CSC 246/446 Machine Learning Instructor: Daniel Gildea
    office hours: Tu/Th 3:00pm-4:00pm, CSB 627
  2. 2015 Fall

    CSC 248/448 Statistical Speech and Language Processing Instructor: Daniel Gildea
    office hours: Mon/Th 3:00pm-4:00pm, CSB 627
  3. 2015 Spring

    CSC 246/446 Machine Learning Instructor: Daniel Gildea