arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.09773cs.SEcs.AI
收藏

面向神经源代码摘要的眼动人类注意力建模

Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization

University of Notre Dame(圣母大学);University of Nebraska - Lincoln(内布拉斯加大学林肯分校)

Aakash Bansal, Bonita Sharif, Collin McMillan

AI总结:

本文利用眼动追踪实验数据构建人类注意力模型,预测源代码中对摘要最重要的单词,并以此增强基线神经代码摘要方法,有效提升了模型的预测性能。

摘要:

神经源代码摘要是指利用神经网络生成源代码行为的自然语言描述的任务。大多数神经模型的一个基本组件是注意力机制。该注意力机制学习将源代码中的特征与生成自然语言描述时要使用的特定单词连接起来。人类在查看代码时也会比其他特征更关注某些特征。这种人类注意力反映了经验和高级认知能力,远远超出了任何当前神经模型的能力。在本文中,我们使用已发表的眼动追踪实验的数据来创建这种人类注意力的模型。该模型预测源代码中哪些单词对代码摘要最为重要。接下来,我们使用我们的人类注意力模型增强了一个基线神经代码摘要方法。我们观察到,增强后的方法在预测性能上有所提升,与其他生物启发的神经模型表现一致。

英文摘要:

Neural source code summarization is the task of generating natural language descriptions of source code behavior using neural networks. A fundamental component of most neural models is an attention mechanism. The attention mechanism learns to connect features in source code to specific words to use when generating natural language descriptions. Humans also pay attention to some features in code more than others. This human attention reflects experience and high-level cognition well beyond the capability of any current neural model. In this paper, we use data from published eye-tracking experiments to create a model of this human attention. The model predicts which words in source code are the most important for code summarization. Next, we augment a baseline neural code summarization approach using our model of human attention. We observe an improvement in prediction performance of the augmented approach in line with other bio-inspired neural models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑