A Convolutional Attention Network for Extreme Summarization of Source Code.
ICML(2016)
摘要
Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the modelu0027s attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. We apply this architecture to the problem of extreme summarization of source code snippets into short, descriptive function name-like summaries. Using those features, the model sequentially generates a summary by marginalizing over two attention mechanisms: one that predicts the next summary token based on the attention weights of the input tokens and another that is able to copy a code token as-is directly into the summary. We demonstrate our convolutional attention neural networku0027s performance on 10 popular Java projects showing that it achieves better performance compared to previous attentional mechanisms.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络