Most tasks in natural language processing can be cast into question answering (QA) problems over language input. We introduce the dynamic memory network (DMN), a unified neural network framework which processes input sequences and questions, forms semantic and episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers. The DMN can be trained end-to-end and obtains state of the art results on several types of tasks and datasets: question answering (Facebook's bAbI dataset), sequence modeling for part of speech tagging (WSJ-PTB), and text classification for sentiment analysis (Stanford Sentiment Treebank). The model relies exclusively on trained word vector representations and requires no string matching or manually engineered features.
Added 4 years ago by Roland Memisevic