Building Interpretable Interaction Trees for Deep NLP Models

No. 16: AAAI-21 Technical Tracks 16

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 35

AAAI Technical Track on Speech and Natural Language Processing III

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.

10.1609/aaai.v35i16.17685