A Natural Language Inference Method Based on Multi-Level Linguistic Information
With the deepening of the network depth layer by layer,When extracting features,many surface information and shallow features are lost more or less,and some reasoning scenarios just need these shallow features to make inference judgments.This thesis proposes a NLI method that introduces multi-layer linguistic information.By learning the contribution weights of different layers of the multi-layer deep neural network to the results,it can effectively combine the linguistic information learned by different layers to predict the results.Through the experi-mental results on the SNLI dataset and the interpretive analysis of multiple samples,it is shown that different layers of the multi-layer deep neural network capture different linguistic information,and different layers are good at different reasoning tasks and reasonably integrate differ-ent linguistic information.The information contributes to the performance improvement of NLI tasks.
natural language processingmulti-level linguistic informationnatural language inferenceattention mechanism
万方数据
维普
