Nguyên Bạch  

Language Technologies Institute                 Phone: (412) 268-5478

School of Computer Sciences                     Fax: (412) 268-6298

Carnegie Mellon University                      Email: nbach@cs.cmu.edu

5000 Forbes Avenue                              http://www.cs.cmu.edu/~nbach/

Pittsburgh, PA 15213-3891

Natural Language Processing, in particular Machine Translation and Information Extraction.  

Special focus on named entity extraction and translation from multi-lingual documents.

Text Mining, Spoken Language Processing, Machine Learning.

CARNEGIE MELLON UNIVERSITY                                           2005 - Present

 LANGUAGE TECHNOLOGY INSTITUTE, SCHOOL OF COMPUTER SCIENCE

 Graduate Research Assistant in InterACT

JOHNS HOPKINS UNIVERSITY                                            2003 -2005

M.S.E. in Computer Science

VIETNAM NATIONAL UNIVERSITY                                          1997-2001  

B.S. in Mathematics and Computer Science with Honors

• Graduate Student Research Fellowship, Carnegie Mellon University        2005 - present
• Vietnam Education Foundation Fellowship                                 2003 - 2005
• Vietnam National University Scholarship                                 1997 - 2001

CARNEGIE MELLON UNIVERSITY                                          2005 – Present

Graduate Research Assistant in the interACT

Major research member of several projects on text and speech translation and named entity extraction and translation, funded by the Defense Advanced Research Projects Agency (DARPA) and the National Science Foundation (NSF).

GALE (The Global Autonomous Language Exploitation)  

Developed core technologies to extract and translate unknown words from Arabic and Chinese into English, and improved the translation quality.

STEEM (Summarization, Translation and Entity Extraction of Multimedia Documents)

Key technology contributor responsible for the semi-unsupervised cross-lingual entity extraction for Arabic, Chinese, and English.

JOHNS HOPKINS UNIVERSITY                                            Summer 2004

Unsupervised Personal Name Disambiguation Cross Documents

Developed effective unsupervised clustering technique over a rich feature space of biographic facts, which are automatically extracted from the Web via a language-independent bootstrapping process.

INSTITUTE OF INFORMATION TECHNOLOGY                           2001–2003

Research Scientist in the Pattern Recognition and Knowledge Engineering Department

Conducted research on Vietnamese speech recognition and synthesis, including Vietnamese acoustic and phonetic features, Fujisaki model for text-to-speech system with prosody features.

·  Hansjoerg Mixdorff, Nguyen Hung Bach, Hiroya Fujisaki, Mai Chi Luong, 'Quantitative Analysis and Synthesis of Syllabic Tones in Vietnamese,' Proceeding of the 8^th European Conference on Speech Communication and Technology (Eurospeech), Sep 2003, pp 177 – 180, Geneva, Switzerland. [PDF]

·  Bạch Hưng Nguyên, Nguyễn Tiến Dũng, Mô hình Fujisaki và áp dụng trong phân tích thanh điệu tiếng Việt, Kỉ yếu Hội thảo Quốc gia: Một số vấn đề chọn lọc của Công nghệ Thông tin, NXB Khoa học kĩ thuật, 2003.

·  Bạch Hưng Nguyên, Lương Chi Mai, Ứng dụng kỹ thuật can chỉnh thời gian động vào nhận dạng từ tiếng Việt đơn lẻ, Tạp chí Khoa Học & Công Nghệ, Số ĐB 2002.