Zhifang Sui

Research on Automatic Construction of Medical Ontology

Using the techniques and theories of natural language processing (NLP), this paper puts forward threads and ways to build automatically domain ontologies based on text content. Through restructuring and utilizing the generally-acknowledged domain knowledge in medical domain, this paper also constructs a concept system of the multidimensional model of modern medicine towards clinic medicine, realizing the automatic construction and acquisition of modern medical knowledge specification system. This further provides theoretical foundation and technical support for automatic construction of professional domain ontologies.

Research on Automatic Chinese Multi-word Term Extraction Based on Integration of Web Information and Term Component

This paper presents an automatic Chinese multi-word term extraction method based on the integration of Web information and term component. We extract candidate terms by identifying delimiters, and filter invalid terms by checking the context terms in the Google result pages that are returned by Google when the candidate term is set as search request. Term component is taken into account to estimate the termhood. Inspired by the economical law of term generating, we propose two measures of a candidate term to be a true term: the first measure is based on domain speciality of term, and the second one is based on the similarity between a candidate and a template that contains structured information of terms. Experiments on IT domain and Medicine domain show that our method is effective and portable in different domains.

The Development of an NLP-Based Chinese Ontology Construction Platform

This paper describes an NLP-based Chinese ontology construction platform developed by the authors. The construction platform is developed based on the open source project Protégé. The paper mainly focuses on two key technologies of automatic construction of ontology—the extraction of attribute value and the automatic generation of ontology hierarchy structure. The paper then introduces how the automatic construction technologies integrate into Protégé in the form of plug-in components, and finally describes the initial ideas for the development of an new ontology construction platform, which makes it possible to construct a large-scale ontology knowledge base.

The Chinese Noun Metaphors Knowledge Base and its Use in the Recognition of Metaphors

This paper presents a method for refining Chinese noun metaphor knowledge base, using two kinds of resources of Grammatical Knowledge Base of Contemporary Chinese (GKB) and Chinese Concept Dictionary(CCD). This utilizes the uniqueness of the storage number in the concept of the CCD and builds on the mapping relations from a source domain to most target domains. At the same time, the description specification of Chinese metaphor knowledge base also inherits some attributives of GKB. In addition, we conduct recognition experiment of noun metaphorical patterns by using knowledge base information. We show that the efficiency on the noun metaphor knowledge base has been proved for the recognition task.

Discriminatively Modeling Commonality of Term Types for Extracting Relation from Small Corpora

In this paper, we present a novel strategy to partly solve the data sparseness problem caused by small corpora in relation extraction by discriminatively modeling commonality among terms in each term type associated with the relation. The key idea is to use the information of terms rather than that of term pairs to extract relations. Based on this idea, terms in each term type were separately extracted from the corpora and a special function, called relation function, is used to determine whether the two terms selected from each term type have the target relation. As we can get more information of terms than that of term pairs in limited corpora, instances of the target relation we get using commonality among terms will be larger in amount and more reliable in quality. This is also proved by the experiments.