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 1908.00588cs.CL
收藏

使用预测语义编码可视化RNN状态

Visualizing RNN States with Predictive Semantic Encodings

Simon Fraser University(西蒙弗雷泽大学)

Lindsey Sawatzky, Steven Bergner, Fred Popowich

摘要:

递归神经网络是一种有效和流行的工具,用于建模序列数据,如自然语言文本。然而,它们的深层性质和大量参数对那些打算精确研究它们如何工作的人构成了挑战。我们提出了一种视觉技术,它在递归神经网络中隐藏状态的语义背后提供了一种高层次的直觉。这种语义编码允许在整个模型中对隐藏状态进行比较,而不依赖于它们的内部细节。所提出的技术显示在概念可视化工具,这是证明可视化的语言建模的自然语言处理任务。

英文摘要:

Recurrent Neural Networks are an effective and prevalent tool used to model sequential data such as natural language text. However, their deep nature and massive number of parameters pose a challenge for those intending to study precisely how they work. We present a visual technique that gives a high level intuition behind the semantics of the hidden states within Recurrent Neural Networks. This semantic encoding allows for hidden states to be compared throughout the model independent of their internal details. The proposed technique is displayed in a proof of concept visualization tool which is demonstrated to visualize the natural language processing task of language modelling.

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。

↑