Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent
Year: 2019
Type: preprint
Abstract: 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%.
Source: arXiv (Cornell University)
Authors: Dai, Zelin, Liu, Weitang, Zhan, Guanhua
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2953962108