1 code implementation • 28 Jan 2020 • Firas Kassawat, Debanjan Chaudhuri, Jens Lehmann
Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input.
Ranked #1 on Goal-Oriented Dialog on Kvret