End-to-end Gated Self-attentive Memory Network for Dialog Response Selection

This paper presents approaches for the noetic end-to-end response selection challenge in DSTC7. Given a pool of response candidates in a dialog history with external domain knowledge, we propose a Gated Self-attentive Memory Network to encode dialog history and external domain knowledge in an end-to-end trainable manner. Our novelty is that each utterance in the memory is enhanced with self-attention building the connection between dialog history and external domain knowledge in a gated multi-hop manner. We ensemble various gated self-attentive memory network with hierarchical GRU baseline models for final submission. Official evaluation results show that our approach ranks at the second place for both student advising and Ubuntu subtasks integrated with external domain knowledge.