AttViz：在线探索自注意力，用于透明神经语言建模
AttViz: Online exploration of self-attention for transparent neural language modeling
摘要：
神经语言模型正在成为查询回答、文本分类、消歧、补全和翻译任务的主流方法。这些神经网络模型通常由数亿个参数组成，以可解释性为代价提供了最先进的性能;人类不再能够跟踪和理解决策是如何做出的。最初为翻译任务引入的注意力机制已成功地用于其他与语言相关的任务。我们提出AttViz，一个在线工具包，用于探索自注意力-与单个文本标记相关的真实值。我们展示了现有的深度学习管道如何产生适合AttViz的输出，以最小的努力在线提供注意力头及其聚合的新颖可视化。我们在新闻片段的例子中展示了如何使用所提出的系统来检查并可能更好地理解模型已经学习（或强调）的内容。
英文摘要：
Neural language models are becoming the prevailing methodology for the tasks of query answering, text classification, disambiguation, completion and translation. Commonly comprised of hundreds of millions of parameters, these neural network models offer state-of-the-art performance at the cost of interpretability; humans are no longer capable of tracing and understanding how decisions are being made. The attention mechanism, introduced initially for the task of translation, has been successfully adopted for other language-related tasks. We propose AttViz, an online toolkit for exploration of self-attention---real values associated with individual text tokens. We show how existing deep learning pipelines can produce outputs suitable for AttViz, offering novel visualizations of the attention heads and their aggregations with minimal effort, online. We show on examples of news segments how the proposed system can be used to inspect and potentially better understand what a model has learned (or emphasized).
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。
