一句话：提出基于 RoBERTa 的问答机器人 DeployQA，通过词汇、预训练与微调三方面领域适配，自动回答软件部署问题。
随着软件系统复杂度与规模不断增长，部署与交付变得越来越困难，开发者往往需要从用户手册和 Stack Overflow 帖子中人工查找答案。本文提出 DeployQA，一个面向软件部署领域的问答机器人，可自动在上述文本资源上回答部署相关问题。系统以 RoBERTa 为基础模型，为弥合自然语言与软件部署领域之间的差距，作者分别从词汇表、预训练和微调三个层面提出了领域适配策略。为支持评测，作者构建了 DeQuAD 数据集，并在其上与多种基线方法进行比较。实验结果表明，借助这三种领域适配策略，DeployQA 的效果显著优于基线方法，验证了领域适配对软件部署问答任务的有效性。
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.
DOI 原文 ·
@inproceedings{paperbot7354,
title = {Answering Software Deployment Questions via Neural Machine Reading at Scale},
author = {Guanjie Qiu and Diwei Chen and Shuai Zhang and Yitian Chai and Xiaodong Gu and Beijun Shen},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3559525}
}