Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent
arXiv:1907.03590
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%.
arXiv comment7 pages, 3 figures submitted to journal
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- LSTM: A Search Space Odyssey
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Proactive Human-Machine Conversation with Explicit Conversation Goals