(Semi) automatic Assertion Generation from Controlled Chinese Natural Language: A Practice in Aerospace Industry
Shiyu Liu, Dongfang Li, Yasha Chen, Guang Zhong Yang · 2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C) · 2021
Due to the effectiveness of assertion based verification (ABV) in programmable logic verification, and the error-proneness and time-consuming of the manual writing of assertions, the research on automatic generation of System Verilog Assertion (SVA) from English has developed rapidly in the past decade. The demand for high reliability verification in the aerospace industry urges us to explore the role of automatic assertion generation in Chinese. In this work, we proposed a controlled Chinese natural language (CCNL) framework to translate natural language assertions (NLA) into SVA. The step of capturing controlled Chinese NLAs from specification documents remains manually, which is the reason for so-called semi-automatic generation. CCNL framework consists of Chinese controlled word list, regular expression based semantic parser and assertion translator. We used this framework to extract assertions from requirements documents in Chinese, evaluated the framework, and proved its effectiveness.