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

arXiv: https://arxiv.org/abs/1907.03590 · HTML: https://mlsanity.com/paper/1907.03590/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2019.

## Built on by (most cited first, 1 of 1)

- [Target-Guided Open-Domain Conversation Planning](https://mlsanity.com/paper/2209.09746/) (2022)

## Abstract (arXiv)

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%.