Global-to-local Memory Pointer Networks for Task-Oriented Dialogue

ICLR 2019  ·  Chien-Sheng Wu, Richard Socher, Caiming Xiong ·

End-to-end task-oriented dialogue is challenging since knowledge bases are usually large, dynamic and hard to incorporate into a learning framework. We propose the global-to-local memory pointer (GLMP) networks to address this issue. In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge. The encoder encodes dialogue history, modifies global contextual representation, and generates a global memory pointer. The decoder first generates a sketch response with unfilled slots. Next, it passes the global memory pointer to filter the external knowledge for relevant information, then instantiates the slots via the local memory pointers. We empirically show that our model can improve copy accuracy and mitigate the common out-of-vocabulary problem. As a result, GLMP is able to improve over the previous state-of-the-art models in both simulated bAbI Dialogue dataset and human-human Stanford Multi-domain Dialogue dataset on automatic and human evaluation.

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Task-Oriented Dialogue Systems KVRET GLMP Entity F1 59.97 # 4
BLEU 14.79 # 4


No methods listed for this paper. Add relevant methods here