Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network

ACL 2018 Xiangyang ZhouLu LiDaxiang DongYi LiuYing ChenWayne Xin ZhaoDianhai YuHua Wu

Human generates responses relying on semantic and functional dependencies, including coreference relation, among dialogue elements and their context. In this paper, we investigate matching a response with its multi-turn context using dependency information based entirely on attention... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Conversational Response Selection Ubuntu Dialogue (v1, Ranking) DAM [email protected] 0.767 # 9
[email protected] 0.874 # 9
[email protected] 0.969 # 9
[email protected] 0.938 # 7

Methods used in the Paper