When a system is developed, requirements document is generated by requirement analysts and then translated to formal specifications by specifiers. If a formal specification can be generated automatically from a natural language requirements document, ... When a system is developed, requirements document is generated by requirement analysts and then translated to formal specifications by specifiers. If a formal specification can be generated automatically from a natural language requirements document, system development cost and system fault from experts' misunderstanding will be decreased. A pronoun can be classified in personal and demonstrative pronoun. In the characteristics of requirements document, the personal pronouns are almost not occurred, so we focused on the decision of antecedent for a demonstrative pronoun. For the higher accuracy in analysis of requirements document automatically, finding antecedent of demonstrative pronoun is very important for elicitation of formal requirements automatically from natural language requirements document via natural language processing. The final goal of this research is to automatically generate formal specifications from natural language requirements document. For this, this , based on previous research [Park07], proposes an anaphora resolution system to decide antecedent of pronoun using natural language processing from natural language requirements document in Korean. This proposes heuristic rules for the system implementation. By experiments, we got 91.34%, 70.31% as recall and precision respectively with ten requirements documents. ，韩语论文网站，韩语毕业论文 |
