论文标题
为深NLP模型构建可解释的交互树
Building Interpretable Interaction Trees for Deep NLP Models
论文作者
论文摘要
本文提出了一种方法，以分解和量化在DNN内部编码的单词之间进行自然语言处理的方法。我们构造了一棵树，以编码DNN提取的显着相互作用。提出了六个指标来分析句子中成分之间相互作用的特性。相互作用是根据shapley单词值定义的，该值被认为是对网络预测的单词贡献的公正估计。我们的方法用于量化在BERT，ELMO，LSTM，CNN和Transformer网络中编码的单词交互。实验结果为了解这些DNN提供了新的观点，并证明了我们方法的有效性。
This paper proposes a method to disentangle and quantify interactions among words that are encoded inside a DNN for natural language processing. We construct a tree to encode salient interactions extracted by the DNN. Six metrics are proposed to analyze properties of interactions between constituents in a sentence. The interaction is defined based on Shapley values of words, which are considered as an unbiased estimation of word contributions to the network prediction. Our method is used to quantify word interactions encoded inside the BERT, ELMo, LSTM, CNN, and Transformer networks. Experimental results have provided a new perspective to understand these DNNs, and have demonstrated the effectiveness of our method.
