We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories. Motivated by the prototype theory in modern linguistics, ProtoryNet makes a prediction by finding the most similar prototype for each sentence in a text sequence and feeding an RNN backbone with the proximity of each sentence to the corresponding active prototype. The RNN backbone then captures the temporal pattern of the prototypes, which we refer to as prototype trajectories. Prototype trajectories enable intuitive and fine-grained interpretation of the reasoning process of the RNN model, in resemblance to how humans analyze texts. We also design a prototype pruning procedure to reduce the total number of prototypes used by the model for better interpretability. Experiments on multiple public data sets show that ProtoryNet is more accurate than the baseline prototype-based deep neural net and reduces the performance gap compared to state-of-the-art black-box models. In addition, after prototype pruning, the resulting ProtoryNet models only need less than or around 20 prototypes for all datasets, which significantly benefits interpretability. Furthermore, we report a survey result indicating that human users find ProtoryNet more intuitive and easier to understand than other prototype-based methods.
翻译:我们提出一个新的可解释的深神经网络,称为ProtoryNet,它基于原型轨迹的新概念。在现代语言原型理论的激励下,ProtoryNet通过在文本序列中找到每个句子最相似的原型,并将每个句子与相应的主动原型相近的 RNN 脊柱装入 RNN 。RNN 骨干随后捕捉了原型的时间模式,我们称之为原型轨迹。原型轨迹使得能够对RNN模型的推理过程进行直观和精细的精确解释,这与人类分析文本的方式相似。我们还设计了一个原型剪裁程序,以减少模型使用的原型总原型,以便更便于解释。对多个公共数据集的实验显示,ProtoryNet比基线原型深神经网更准确,并比我们称之为最先进的黑箱模型模型缩小了性差。此外,在原型修饰后,所产生的ProtoryNet模型模型只需要少于或大约20个原型的人类分析文本文本。我们更了解了所有数据原型用户的原型模型。