Ding Liu
dliu@cs.rochester.edu

I am a PhD candidate at CS department, University of Rochester . My research interest focuses on using syntactic and semantic features to improve Statistical Machine Translation. In particular, I am investigating statistical models which can efficiently integrate the comprehensive syntactic and semantic features into a Tree-to-String based MT system. I am in the MT group led by Prof. Daniel Gildea.


Machine Translation

  • Semantic Role Features for Machine Translation, Ding Liu and Daniel Gildea. To appear in the 23rd International Conference on Computational Linguistics (COLING 2010).
  • Bayesian learning of Phrasal Tree-to-String Templates, Ding Liu and Daniel Gildea. In Conference on Empirical Methods in Natural Language Processing (EMNLP-09), Singapore, 2009.
  • Improved Tree-to-string Transducer for Machine Translation. Ding Liu and Daniel Gildea. In Proceedings of the 3rd Statistical Machine Translation Workshop, associated with ACL2008., Columbus, Ohio, 2008.
  • Maximum Correlation Training for Machine Translation Evaluation, Ding Liu and Daniel Gildea. In Proceedings of the Association for Computational Linguistics, North American Chapter (NAACL-07), Rochester, NY, 2007.
  • Stochastic Iterative Alignment for Machine Translation Evaluation, Ding Liu and Daniel Gildea. In Proceedings of the International Conference on Computational Linguistics/Association for Computational Linguistics (COLING/ACL-06) Poster Session, Sydney, 2006.
  • Syntactic Features for Evaluation of Machine Translation, Ding Liu and Daniel Gildea. In ACL 2005 Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, 2005.
  • Automatic Evaluation of Sentence Fluency, Ding Liu, Yu Zhou, Chengqing Zong, Fuj i Ren. In Proc. IEEE International Conference on Systems, Man & Cybernetics., Washington, D.C, USA. October 2003.