no code implementations • 11 Nov 2019 • Zhuoxuan Jiang, Ziming Huang, Dong Sheng Li, Xian-Ling Mao
In this paper, we propose a novel joint end-to-end model by multi-task representation learning, which can capture the knowledge from heterogeneous information through automatically learning knowledgeable low-dimensional embeddings from data, named with DialogAct2Vec.