Hendra Setiawan (张云祥)
I am a postdoctoral researcher working in the Computational Linguistics and Information Processing (CLIP) lab at the University of Maryland, Institute for Advanced Computer Studies. I am working with Philip Resnik on Statistical Machine Translation. Prior to this, I was a postgraduate student at the School of Computing, National University of Singapore, co-advised by two wonderful supervisors: Haizhou Li (I2R) and Min-Yen Kan. At NUS, I was affiliated to the Web Information Retrieval / Natural Language Processing (WING) Group.
My broad research interest is the application of statistical methods to natural language problems. Specifically, I've been looking at practical ways to approximate linguistic knowledge (both syntactic and semantic) using easy-to-obtain and readily-available statistics, rather depending on linguistically-annotated data that is often impractical to obtain. My research motto has always been: "Beat the data until it confesses". So far, I survive -- check out my publications on approximating syntactic knowledge via models based on function words which are approximated with most frequent words in the corpus. Having said that, I now am looking at ways to utilize existing annotated-data to be applied to word alignment modeling.
Most of the models that I developed will be available features in cdec -- the fastest hierarchical phrase-based translation system developed by Chris Dyer.
I'll be in the job market soon!!! CV and recommendations are available upon request. Please contact: hendra _at_ umiacs _dot_ umd _dot_ edu
My more famous self is a leading men's double badminton player, who won several Olympics medals including one gold.
Selected Publications:
Hendra Setiawan, Chris Dyer and Philip Resnik. Discriminative Word Alignment with a Function Word Reordering Model To appear in Proc. of The 2010 Conference on Empirical Methods on Natural Language Processing (EMNLP), 2010.
Hendra Setiawan and Philip Resnik. Generalizing Hierarchical Phrase-based Translation using Rules with Adjacent Nonterminals. In Proc. of North America chapter of Association for Computational Linguistics (NAACL), 2010.
Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonathan Weese, Ferhan Ture, Phil Blunsom, Hendra Setiawan, Vladimir Eidelman, and Philip Resnik. cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models. To appear in Proceedings of Association for Computational Linguistics (ACL Demonstration track), 2010.
Hendra Setiawan, Min-Yen Kan, Haizhou Li and Philip Resnik. Topological Ordering of Function Words in Hierarchical Phrase-based Translation. In Proc. of The Annual Meeting of Association for Computational Linguistics, 2009.
Chris Dyer, Hendra Setiawan, Yuval Marton, and Philip Resnik. The University of Maryland Statistical Machine Translation System for the Third Workshop on Machine Translation. In Proc. of the EACL-2009 Workshop on Statistical Machine Translation, 2009.
Hendra Setiawan, Min-Yen Kan, and Haizhou Li. Ordering Phrases with Function Words. In Proc. of The Annual Meeting of Association for Computational Linguistics, 2007.
Min Zhang, Haizhou Li, Jian Su, and Hendra Setiawan. A Phrase-based Context-dependent Joint Probability Model for Named Entity Translation. In Proc. of The Second International Joint Conference on Natural Language Processing, 2005.
Contact Information:
Last Updated: Thu May 27 17:21:20 EDT 2010