About NLPlab

Northeastern University is located at the beautiful lakeside of Shenyang Nanhu Park. Mr. Chang Hsueh-liang, the well-known young marshal, once acted as the president. Natural Language Processing Lab of Department of Computer Science of Northeastern University is a high-tech research base, which focuses on scientific research, industry development and basic course education. The research work is directed by Prof. Yao Tian-shun and Prof. Zhu Jing-bo. The lab now has a station for postdoctoral programs.

In 1980, the lab first got involved in the area of machine translation when Prof. Yao Tianshun started his work as a visiting scholar at Kongandao Machine Translation Research Center of Chinese University of Hong Kong.

In 1984, the NLP group designed and implemented a Chinese-English machine translation model based on Schank’s conceptual depending theory.

From 1987 to 1994, we took part in the research of CICC Asian multilingual machine translation system (including China, Japan, Thailand, Malay, Indonesia etc.), which was directed by European Community. Our lab is responsible for the research on Chinese analysis. We first cooperated with Nippon Electric Co, LTD, then Fujitsu Company. After we finished the work for CICC in 1989, we finished building our own Chinese-English machine translation system.

From 1990 to 1994, we worked on the “905 project” which was granted by the Electronic Department and Commission of Science Technology and Industry for National Defense. This project is called CIPP: the research and implementation of Chinese Information Processing Platform.

Since 1992, the lab has undertaken nine projects on natural language processing granted by National Natural Science Fund.

1. The Understanding of Chinese Written Text; (6865003)
   
2. Understanding-oriented Chinese-English Machine Translation-Theory and Methodology; (6875023)
   
3. General Interface for Chinese Text Analysis; (69083301)
   
4. Chinese Full Text Understanding System; (69285006)
   
5. The design and implementation of a Chinese-English-Japanese Multilingual Machine Translation Information Sharing System; (69485008)
   
6. The design and implementation of a Chinese-English-Korean Multilingual Machine Translation System; (69675019) 1997-1999
   
7. Chinese Analysis Theory and Methodology Based on predication semantic combination; (69683004) 1997-1999
   
8. A practical system of Chinese-English-Korean Multilingual Machine Translation; (69985001) 2000-2002
   
9. Extend-chunk based Machine Translation System; (60083006) 2001-2003
   

In 1992, we collaborated with Hong Kong State University on the study of “Automatic Text Summary” using our language analyzer. From then on, the two sides have never ceased cooperation.

In 1992, we are accredited to take up the projects of “Basic Research on the Understanding of Chinese and Other Languages(863-306-05-05-B)” and “Machine Translation Technology and System (863-306-03-06-1)” by the expert group of National High-tech Intelligent Computer System.

In 1993, oweing to the work of our lab, Prof. Yao Tian-shun was elected the Director of International Oriental Language Computer Society and has been on that position all along.

In Dec 1995, the scientific monograph -- Natural Language Processing- A research of making computers understand human languages was published by the publishing publisher of Tsinghua University.

From 1995 to 2000, we initiated the research on Chinese-English-Korean Multilingual Machine Translation system together with Korean Pohang University of Science and Technology, and completed the work successfully.

In 1997, we took up the mission from American BERLITZ Translation Company of translating Kreisler’s Automobile Manual into many languages with the help of computers, and our translation was publicly published in USA.

In 1998, we took part in the National Key Project for Basic Research: Image, Voice, Natural Language Understanding and Knowledge Discovery. We are responsible for the evaluation of Chinese-English Machine Translation system (G19980305011). This is the first fully automatic evaluation project of machine translation ever launched in China.

In 1999 we started the research on linguistics preprocessing of TTS (Text of Speech) together with Motorola Chinese Research Center and provided them with Chinese analyser. Finally we completed the research task on the contract.

In 2002, approved by the Department of Science and Technology, we cooperated with Korean Pohang University of Science and Technology to develop “Chinese-Korean Machine Translation System(CK99-03).

In 2002, we took up the project of “content identification and information filtering technology (863-301-7-7)” which was granted by the expert group of National High-tech Intelligent Computer System.

In 2001, we worked together with Panasonic Information and Networking Technology Laboratory of Princeton, USA on the research of network OCR linguistic postprocessing. The first step has been finished, the next step will be constructing language model, and the final task of the project will be accomplished next year.

In May 2002, the scientific monograph -- Natural Language Processing- A research of making computers understand human languages (second edition) was published by the publishing company of Tsinghua University for the second time.

It can be seen that after two decades' hard work, our lab has evolved into a research group with members of all ages, high international prestige, firm theory and practice foundation, and the ability of developing industry. We will still work hard to achieve more success.

A survey of resources

During the last two decades our group has accumulated and accomplished:

• A Chinese tree library of one million and a tagged Chinese Corpora of five million
  
• An electronic Chinese dictionary of 170 thousand words
  
• An electronic English dictionary of 80 thousand words
  
• An electronic dictionary of 26 types of specialties
  
• An English word library of 260 thousand words and its operating software
  
• A Chinese surname library of three thousand
  
• A basic name library of four thousand
  
• A feature library of 300 thousand (dynamic semantic library)
  
• Wordnet of Chinese nouns and verbs
  
• Developed a Chinese-English-Korean Multilingual Machine Translation system under cooperation
  
• A Chinese-English two-way machine translation system (CETRAN)
  
• A complete design of middle language and rule description language and the compiler