Introduction to Our Lab.

Natural Language Processing (NLP) studies how computer systems understand and generate human languages. The history of this research field is very old. After the invention of computers, many organizations have been engaged in the developments of new theories and technologies for NLP. Because languages are indispensable media for human communication, the applications of the research results are very wide, for example, bioinformatics, Internet, intelligent information retrieval, machine translation, man-machine interface, speech recognition and generation, OCR (OLCR), text processing, written-aids, computer-aided instruction, etc.

The Natural Language Processing Laboratory at National Taiwan University has been set up for several years. Now it is supervised by Professor Hsin-Hsi Chen . Within these years, many research results are presented in journals, conference proceedings and books. Besides publication of papers, many systems are implemented and are demonstrated .

The main research interests includes:

  (1) Multilingual Information Management

• This research studies classification, retrieval, filtering, extraction, and summarization of multilingual data.

  (2) Language Engineering

• The research studies how to represent, acquire, employ, and integrate linguistic knowledge.

  (3) Native Language Processing

• Besides the researches on Chinese, we also extend the results into Taiwanese, Hakka, and even Austronesian language processing.

Now the following research topics are investigated:

  (1) Cross-Language Information Retrieval

  (2) Information Extraction & Bioinformatics

  ((3) Question and Answering

  (4) Summarization

  (5) Topic Detection and Tracking

  (6) Web Mining

Achievements