Title :
Automatic extraction of definitions
Author :
Zhang, Chunxia ; Jiang, Peng
Author_Institution :
Sch. of Software, Beijing Inst. of Technol., Beijing, China
Abstract :
The task of definition extraction aims to acquire definitions of terms from texts. This task is a subtask of terminology extraction, ontology construction, semantic relation learning, and question answering and so on. This paper presents a bootstrapping approach to automatic extracting definitions of domain-specific terms from unannotated Chinese free texts. Experimental results in three domains of computer, military, and archaeology show effectiveness of our algorithm. As an application of definition extraction, definitions identified by our method have been used to answer factual questions in a question answering system.
Keywords :
data mining; information retrieval; learning (artificial intelligence); natural language processing; ontologies (artificial intelligence); text analysis; archaeology domain; automatic definition extraction; bootstrapping approach; computer domain; data mining; domain-specific term; military domain; ontology construction; question answering system; semantic relation learning; terminology extraction; unannotated Chinese free text; Classification algorithms; Computer science; Filtering; Machine learning; Machine learning algorithms; Military computing; Ontologies; Software; Sun; Terminology; bootstrapping method; definition extraction; domain-specific ontology; knowledge extraction; question answering;
Conference_Titel :
Computer Science and Information Technology, 2009. ICCSIT 2009. 2nd IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4519-6
Electronic_ISBN :
978-1-4244-4520-2
DOI :
10.1109/ICCSIT.2009.5234687