A Model for Processing Temporal References in Chinese

Information Extraction (IE) is an upcoming challenging research area to cope with the increasing volume of unwieldy, distributed information resources, such as information over Among them, temporal information is important in domains where the task of extracting and tracking information over time occurs frequently, such as planning, scheduling, and question-answering. It may be as simple as an explicit or direct expression in a written language, such as '‘the company closed down in May, 1997''; or it may be left implicit, to be recovered by readers from the surrounding texts. For example, one may know the fact that '‘the company closed down before an earth- quake’', yet without knowing the exact time of the bankruptcy.