As software systems continue to grow in complexity and scale, deploying and delivering them becomes increasingly difficult. In this work, we develop DeployQA, a novel QA bot that automatically answers software deployment questions over user manuals and Stack Overflow posts. DeployQA is built upon RoBERTa. To bridge the gap between natural language and the domain of software deployment, we propose three adaptations in terms of vocabulary, pre-training, and fine-tuning, respectively. We evaluate our approach on our constructed DeQuAD dataset. The results show that DeployQA remarkably outperforms baseline methods by leveraging the three domain adaptation strategies.

Guan Jie Qiu

School of Software, Shanghai Jiao Tong University

Diwei Chen

School of Software, Shanghai Jiao Tong University

Shuai Zhang

School of Software, Shanghai Jiao Tong University

Yitian Chai

School of Software, Shanghai Jiao Tong University

Xiaodong Gu

Shanghai Jiao Tong University, China

China

Beijun Shen

School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University