MULTI PATH TRAINING FRAMEWORK FOR DATA-DRIVEN OPEN-DOMAIN CONVERSATION SYSTEM
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)(2021)
摘要
Nowadays, web data is often used to train a dialogue system. However, noises in web data can disturb the training process, as well as can impact the performance. Consequently, dialogue models tend to be brittle when receiving noisy inputs during the inference. This paper proposes a novel framework, Multi-Path Training (MPT), for training a robust dialogue response generation system. MPT improves the robustness to the noisy training data and the noisy inference queries using three paths. Experimental results show MPT can outperform baselines using the same backbone model, and also prove MPT can improve the robustness to the noise in both the training and inference stage.
更多查看译文
关键词
Seq2Seq, dialogue, robustness, noise
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要