Background:
Research and development in the information processing for the Chinese language are a vital part for the economic growth in Hong Kong. Being a bilingual society with the additional unique Cantonese dialect, Hong Kong must work on issues related to language processing and system development by our own people live and work in Hong Kong. Greater economic and political ties between Hong Kong and China also demand more technical awareness and advancement in Chinese computing in order to support the development of information technologies both in the technical and managerial aspect.
Examples of technical need are abundant: the production of technical manuals in Chinese using machine translation software, telephone answering systems with speech recognition and synthesis capabilities, Chinese computer aided learning packages and English-Chinese bilingual information retrieval systems for Intranet and Internet applications, Information extraction and abstraction, Cantonese speech processing and intelligent input systems. Chinese and bilingual natural language understanding is the fundamental in all these technical areas. Managerial need of Chinese computing is in the effective technical communication in order to lead programmers towards successful design and implementation of Chinese software systems and possibly other large-alphabet languages as well (e.g. Japan and Korean).
The Dept has for many years had an established Chinese Computing lab, and some members in the lab are getting regional and international recognitions, and we do receive consultations on Chinese computing related issues from the Government, different industry sectors, and the news media.
Members: Edmond Chan, Edward Ho, Wen Jie Li, James N.K. Liu, Qin Lu, Vincent Ng (to be confirmed), Grace Ngai, Simon Shiu
Director: Qin Lu
Director's responsibility:
Organize and coordinate group activities; manage lab resources including lab space, facility, software and other resources.
Expertise of members related to the lab:
Edmond Chan: |
Intelligent systems for financial systems |
Edward Ho: |
Information retrieval, information extraction and summarization |
Wen Jie Li: |
Information retrieval and data abstraction |
James Liu: |
Information extraction, Abstraction, Machine translation |
Qin Lu: |
Open Systems and Standardization, Computational Linguistics, Chinese text-to-speech systems |
Vincent Ng: |
Data compression and database systems |
Simon Shiu: |
Document retrieval and comparison using case-based reasoning, soft computing techniques for building intelligent information system |
Joining the Lab:
Any academic staff in COMP who are interested in Chinese Computing especially who has been working in related field are welcome to join at anytime. A member by agreeing to join the lab can share the lab facility and resources commonly available to members. Each member is also obligated to join lab organized activities and making active contribution to lab activities.
Research and Development Focus:
At the present time, the lab has three main areas of research work. The first area is on natural language understanding using computational linguistics techniques with the gradual accumulation of Chinese natural language knowledge-bases and systems such as Chinese natural language parsers, shallow tree banks, collocation databases, etc. The second area is on information retrieval and information extraction. This area needs to make use of the results from the first area. Practical systems can be built for information retrieval and information extraction/abstraction. The third area is in Cantonese speech related processing including, speech synthesis, text-to-speech conversion, phonetic-to-text conversion, etc.
External Collaborators:
- Prof. Yu Shi Wen, Acting Director, Institute of Computational Linguistics, Peking University, expertise in Chinese computational linguistics and received numerous grants from Chinese National Science Foundation and corporate supports.
- Prof. Song Rou, Head, Dept. of Computer Science, Beijing Language and Culture University, expertise in Chinese processing systems, segmentation, information extraction, and practical systems.
- Prof. C.C. Cheng, Head, Dept. of Chinese, Translation, and Linguistics, City U of Hong Kong, Member of the Academy of Sciences, Taiwan , experts in Chinese language, dialects, and computer aided teaching of Chinese.
- Dr. Wong Kam Fai, Dept. of System Engineering, The Chinese University of Hong Kong, expertise in information retrieval, categorization, and extraction.
Partial List of Funded Projects Related to Chinese Computing:
Project Name |
PI |
Amount |
Source of Funding |
Determination of Temporal Reference in Chinese News Articles |
Li Wenjie |
$ 433,404 |
CERG |
Automatic Acquisition of Chinese Collocations with High Precision |
Lu Qin |
$ 543,712 |
CERG |
Standardization on Cantonese Romanization and the Building Blocks for Phonetic Based Applications |
Lu Qin |
$ 2,162,000 |
ITF |
Building Blocks of ISO 10646 Migration in Hong Kong |
Lu Qin |
$ 3,657,600 |
ITF |
Building Resources and Tools for Chinese Computing Lab |
Lu Qin
(For CCL) |
$ 125,000 |
Central |
Semantic Chunking for Web Queries |
Ng Vincent |
$ 469,600 |
CERG |
Combining Co-training and Active Learning for Resource-Aware Named-Entity Recognition |
Ngai Grace |
$ 200,000 |
Central |
Automatic Deduction of Bilingual Semantic Networks from Corpora |
Ngai Grace |
$ 300,000 |
Dept'l |
Adaptation Guided Retrieval of Text-Based Cases : A Neuro-Fuzzy Approach |
Shiu Simon |
$ 472,817 |
CERG |
|