Domain-specific term extraction from free texts

Domain-specific term extraction is a subtask of domain-specific ontology construction, and has been applied into text classification, information retrieval, question answering, automatic indexing, and machine translation and so on. In this paper, we propose an iterative bootstrapping approach to extracting domain-specific terms from un-annotated Chinese free texts. The strings whose internal components are with more probabilities being inside domain-specific terms are identified as candidate terms. Experimental results on three domains of computer, military, and archaeology demonstrate the effectiveness and domain independent nature of our approach.