Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent.
2019
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% on the DuConv dataset. In particular, the ensemble methods further significantly outperform the baseline by 35.85%.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
23
References
0
Citations
NaN
KQI