A design of temporal event extraction from Chinese financial news

摘要

This paper presents an information system for Chinese Information Extraction from Financial news (CHIEF). The ultimate target of the system is to extract information concerning the occurrence time and places of the financial activities in the different companies from a local Hong Kong newspaper, namely 大公報 (Tao Kung Pao). To facilitate event extraction purpose, two groups of templates were defined, i.e. the company related and company restructuring templates. They are used to select the desired information for each type of financial activities, such as 破產 (bankruptcy) or 合併 (merge). Each specific event is then represented using a frame-based knowledge structure. Two types of slots are embedded in each frame: they are the activity- and time-related slots. Based on these slots, multiple activities are interconnected according to their entity relations, temporal relations or the deduced relations. Effectively, CHIEF is a question-answering system designed for handling the company related queries, event based queries, temporal queries and complex queries in a finance domain.