Resource-based Natural Language Processing

Abstract

Research on natural language processing (NLP) started with so-called rule-based methodology, however, compilation of huge amount of grammar rules and dictionary entries are too difficult to develop practical systems. Then, trend of NLP research shifted to corpus-based, or statistical systems. Thanks to the rapid improvement of computer power and data storage, nowadays we can utilize huge amount of actual linguistic data. Combining such linguistic resources and high quality language analyzer, we can extract useful linguistic information and develop practical systems for specific domain. However, the future direction of NLP is still not obvious. Fusion of knowledge and example, or knowledge processing using linguistic resources, is one of the possibilities to develop high-performance NLP systems. As for the research target, machine translation with new paradigm and information retrieval as practical tasks are promising. To realize the fusion of knowledge and example, we try to make a computer system that utilizes linguistic knowledge of different degrees of abstraction as humans do, to make a model of human language function based on the system, and to acquire knowledge on how do humans store and use this kind of knowledge in their minds.