Learn More
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(More)
Coreference resolution is a complex structure prediction task which is usually solved in two steps of first detecting all mentions and then determining their coreference. Similarly to POS tagging we model mention detection as a sequence tagging problem but where the task is to predict a pair of symbols for every position corresponding to the number of(More)
  • 1