Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent

07/08/2019
by   Zelin Dai, et al.
1

Multiple sequence to sequence models were used to establish an end-to-end multi-turns proactive dialogue generation agent, with the aid of data augmentation techniques and variant encoder-decoder structure designs. A rank-based ensemble approach was developed for boosting performance. Results indicate that our single model, in average, makes an obvious improvement in the terms of F1-score and BLEU over the baseline by 18.67 In particular, the ensemble methods further significantly outperform the baseline by 35.85

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset