An NLP-Based Approach for Detecting Ambiguity of Thai Software Requirements Specification

Writing software requirements in the form of natural language especially Thai language is very challenging. If software engineers do not have good writing skills, this may cause the ambiguity resulting in misunderstanding and misinterpretation during the development. To prevent this occurrence, this paper presents an NLP-based approach for detecting ambiguity of Thai software requirements. This approach influences an initiative fundamental of ambiguity detection mechanism at lexical level. The words potentially causing the ambiguity in software requirements are detected and classified into the ambiguity type. The contribution of the approach is demonstrated with the development of a prototype tool, Software Requirement Ambiguity Detector (SRAD). The validation and evaluation results with real software requirements from the various system domains with the practical expert perspective confirm the benefits of the proposed approach and developed tool. In the future, our tool and model will be integrated to our redesigned approach for writing Thai software requirements specification.