一句话：提出 DSM 工具，用 RNN 语言模型从执行轨迹中挖掘有限状态自动机形式规约。
形式规约重要但常缺失，且人工编写耗时、依赖开发者技能。DSM 面向该问题：输入一组执行轨迹，训练循环神经网络语言模型（RNNLM）；由轨迹构造前缀树接受器（PTA），并利用训练好的 RNNLM 提取特征。随后，这些特征被送入聚类算法，用于合并 PTA 中相似的自动机状态，从而组装出多个有限状态自动机（FSA）候选。工具再用模型选择启发式估计各 FSA 的 F-measure，并输出估计值最高的自动机。其实现还提供若干选项，允许用户优化所得 FSA 的质量。
Formal specifications are important but often unavailable. Furthermore, writing these specifications is time-consuming and requires skills from developers. In this work, we present Deep Specification Miner (DSM), an automated tool that applies deep learning to mine finite-state automaton (FSA) based specifications. DSM accepts as input a set of execution traces to train a Recurrent Neural Network Language Model (RNNLM). From the input traces, DSM creates a Prefix Tree Acceptor (PTA) and leverages the inferred RNNLM to extract many features. These features are then forwarded to clustering algorithms for merging similar automata states in the PTA for assembling a number of FSAs. Next, our tool performs a model selection heuristic to approximate F-measure of FSAs, and outputs the one with the highest estimated F-measure. Noticeably, our implementation of DSM provides several options that allows users to optimize quality of resultant FSAs.
DOI 原文 ·
@inproceedings{paperbot4611,
title = {DSM: a specification mining tool using recurrent neural network based language model},
author = {Tien-Duy B. Le and Lingfeng Bao and David Lo},
booktitle = {FSE},
year = {2018},
doi = {10.1145/3236024.3264597}
}