@INPROCEEDINGS{zhang2001mtsummit,
   AUTHOR = {Ying Zhang and Ralf Brown and Robert E. Frederking and Alon Lavie},
   TITLE = {Pre-processing of Bilingual Corpora for Mandarin-English EBMT},
   BOOKTITLE = {Proceedings of MT Summit VIII},
   YEAR = {2001},
   pages = {385-390},
   address = {Santiago de Compostela, Spain},
   month = {September},
}

@INPROCEEDINGS{zhang2003nlpke,
   AUTHOR = {Ying Zhang and Stephan Vogel and Alex Waibel},
   TITLE = {Integrated Phrase Segmentation and Alignment Algorithm for Statistical Machine Translation},
   BOOKTITLE = {Proceedings of International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE'03)},
   YEAR = {2003},
   address = {Beijing, China},
   month = {October},
}

@INPROCEEDINGS{vogel2003mtsummit,
   AUTHOR = {Stephan Vogel and Ying Zhang and Fei Huang and Alicia Tribble and Ashish Venogupal and Bing Zhao and Alex Waibel},
   TITLE = {The {CMU} Statistical Translation System},
   BOOKTITLE = {Proceedings of MT Summit IX},
   YEAR = {2003},
   address = {New Orleans, LA},
   month = {September},
}

@INPROCEEDINGS{zhang2004eamt,
   AUTHOR = {Ying Zhang and Stephan Vogel},
   TITLE = {An Efficient Phrase-to-Phrase Alignment Model for Arbitrarily Long Phrase and Large Corpora},
   BOOKTITLE = {Proceedings of the Tenth Conference of the European Association for Machine Translation (EAMT-05)},
   YEAR = {2005},
   address = {Budapest, Hungary},
   month = {May},
   organization = {The European Association for Machine Translation},
}

@INPROCEEDINGS{zhang2004lrec,
   AUTHOR = {Ying Zhang and Stephan Vogel and Alex Waibel},
   TITLE = {Interpreting Bleu/NIST scores: How much improvement do we need to have a better system?},
   BOOKTITLE = {Proceedings of the 4th International Conference on Language Resources and Evaluation},
   YEAR = {2004},
   address = {Lisbon, Portugal},
   month = {May},
   organization = {The European Language Resources Association (ELRA)}
}

@INPROCEEDINGS{zhang2004tmi,
   AUTHOR = {Ying Zhang and Stephan Vogel},
   TITLE = {Measuring Confidence Intervals for the Machine Translation Evaluation Metrics},
   BOOKTITLE = {Proceedings of The 10th International Conference on Theoretical and Methodological Issues in Machine Translation},
   YEAR = {2004},
   month = {October},
}

@inproceedings{zhang2005sigir,
   author = {Ying Zhang and Fei Huang and Stephan Vogel},
   title = {Mining translations of OOV terms from the web through cross-lingual query expansion},
   booktitle = {SIGIR '05: Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval},
   year = {2005},
   isbn = {1-59593-034-5},
   pages = {669--670},
   location = {Salvador, Brazil},
   doi = {http://doi.acm.org/10.1145/1076034.1076182},
   publisher = {ACM Press},
   address = {New York, NY, USA},
}

@InProceedings{huang2005hlt,
   author = {Huang, Fei and Zhang, Ying and Vogel, Stephan},
   title = {Mining Key Phrase Translations from Web Corpora},
   booktitle = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
   month = {October},
   year = {2005},
   address = {Vancouver, British Columbia, Canada},
   publisher = {Association for Computational Linguistics},
   pages = {483--490},
   url = {http://www.aclweb.org/anthology/H/H05/H05-1061},
}

@InProceedings{zhang2005wpt,
   author = {Zhang, Ying and Vogel, Stephan},
   title = {Competitive Grouping in Integrated Phrase Segmentation and Alignment Model},
   booktitle = {Proceedings of the ACL Workshop on Building and Using Parallel Texts},
   month = {June},
   year = {2005},
   address = {Ann Arbor, Michigan},
   publisher = {Association for Computational Linguistics},
   pages = {159--162},
   url = {http://www.aclweb.org/anthology/W/W05/W05-0829}
}

@INPROCEEDINGS{zhang2006emnlp,
   AUTHOR = {Ying Zhang and Almut Silja Hildebrand and Stephan Vogel},
   TITLE = {Distributed Language Modeling for N-best List Re-ranking},
   booktitle = {Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing},
   month = {July},
   year = {2006},
   address = {Sydney, Australia},
   publisher = {Association for Computational Linguistics},
   pages = {216--223},
   url = {http://www.aclweb.org/anthology/W/W06/W06-1626}
}

@INPROCEEDINGS{hsiao2006icslp,
   AUTHOR = {Roger Hsiao and Ashish Venugopal and Thilo Kohler and Ying Zhang and Paisarn Charoenpornsawat and Andreas Zollmann and Stephan Vogel and Alan W Black and Tanja Schultz and Alex Waibel},
   TITLE = {Optimizing Components for Handheld Two-way Speech Translation for an English-Iraqi Arabic System},
   BOOKTITLE = {Proceedings of the Ninth International Conference on Spoken Language Processing (ICSLP 2006)},
   YEAR = {2006},
   address = {Pittsburgh, PA},
   month = {Sep 17-21},
   abstract = {
     This paper described our handheld two-way speech translation system
     for English and Iraqi. The focus is on developing a field usable
     handheld device for speech-to-speech translation. The computation
     and memory limitations on the handheld impose critical
     constraints on the ASR, SMT, and TTS components. In this paper
     we discuss our approaches to optimize these components for
     the handheld device and present performance numbers from the
     evaluations that were an integral part of the project. Since one major
     aspect of the TransTac program is to build fieldable systems,
     we spent significant effort on developing an intuitive interface that
     minimizes the training time for users but also provides useful information
     such as back translations for translation quality feedback.
     Index Terms: English-Iraqi Speech Translation, Handheld Devices,
     Iraqi Speech Recognition, Translation Infterface, Pocket Translation.
   },
}

@TECHREPORT{zhang2006techreport,
   AUTHOR = {Ying Zhang and Stephan Vogel},
   TITLE = {Suffix array and its applications in empirical natural language processing},
   INSTITUTION = {Language Technologies Institute, School of Computer Science, Carnegie Mellon University},
   YEAR = {2006},
   type = {Technical Report},
   number = {CMU-LTI-06-010},
   address = {Pittsburgh, PA},
   month = {Dec.},
}

@INPROCEEDINGS{zhang2007pandora,
   AUTHOR = {Ying Zhang and Stephan Vogel},
   TITLE = {PanDoRA: A Large-scale Two-way Statistical Machine Translation System for Hand-held Devices},
   BOOKTITLE = {Proceedings of MT Summit XI},
   YEAR = {2007},
   address = {Copenhagen, Denmark},
   month = {Sep},
   abstract = {Statistical machine translation (SMT) approach has taken a lead place in the field of Machine Translation for its performance and low cost in training. However a SMT system demands large amount of resources for its statistical models and can not be run directly on hand-held devices. Most existing translation systems on hand-held devices are either interlingua-based system which requires human effort in writing the grammar rules and not easily adaptable to new domains, or employ a client/server approach where the PDA acts as a client to communicate with a translation server. In this paper we present PanDoRA, a two-way phrase-based statistical machine translation system for stand-alone hand-held devices such as PDAs. With special features such as integerized computation and compact data structure, PanDoRA has been successfully applied in a speech-to-speech translation system with real-time translation speed running on off-the-shelf PDAs. PanDoRA has a capacity of 64K words vocabulary and 4 billion phrase pairs for each translation direction. To our knowledge, PanDoRA is the first large-scale SMT system with build-in reordering models running on hand-held devices. Our experiments show that the translations generated by PanDoRA are of the same quality as the state-of-the-art phrase-based statistical machine translation system such as Pharaoh and STTK which run on PCs. },
   keywords = {Speech Translation, PDA, Handheld-device, Statistical Machine Translation},
}

since Dec. 4, 2006