Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
Authors:
Preprint
Abstract
End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this issue. Mem2Seq is the first neural generative model that combines the multi-hop attention over memories with the idea of pointer network. We empirically show how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories. In addition, our model is quite general without complicated task-specific designs. As a result, we show that Mem2Seq can be trained faster and attain the state-of-the-art performance on three different task-oriented dialog datasets.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Learning to Attend, Copy, and Generate for Session-Based Query Suggestion2017
- A Hierarchical Latent Variable Encoder-Decoder Model for Generating DialoguesProceedings of the AAAI Conference on Artificial Intelligence, 2017
- A Network-based End-to-End Trainable Task-oriented Dialogue System2017
- Hybrid computing using a neural network with dynamic external memoryNature, 2016
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2016
- POMDP-Based Statistical Spoken Dialog Systems: A ReviewProceedings of the IEEE, 2013
- Example-based dialog modeling for practical multi-domain dialog systemSpeech Communication, 2009
- Partially observable Markov decision processes for spoken dialog systemsComputer Speech & Language, 2007
- BLEU2001
- A stochastic model of human-machine interaction for learning dialog strategiesIEEE Transactions on Speech and Audio Processing, 2000