当前位置:
X-MOL 学术
›
arXiv.cs.CL
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
arXiv - CS - Computation and Language Pub Date : 2020-06-30 , DOI: arxiv-2006.16779 Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, Xinchao Xu
arXiv - CS - Computation and Language Pub Date : 2020-06-30 , DOI: arxiv-2006.16779 Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, Xinchao Xu
To build a high-quality open-domain chatbot, we introduce the effective
training process of PLATO-2 via curriculum learning. There are two stages
involved in the learning process. In the first stage, a coarse-grained
generation model is trained to learn response generation under the simplified
framework of one-to-one mapping. In the second stage, a fine-grained generation
model and an evaluation model are further trained to learn diverse response
generation and response coherence estimation, respectively. PLATO-2 was trained
on both Chinese and English data, whose effectiveness and superiority are
verified through comprehensive evaluations, achieving new state-of-the-art
results.
中文翻译:
PLATO-2:通过课程学习构建开放域聊天机器人
为了构建高质量的开放域聊天机器人,我们通过课程学习介绍了 PLATO-2 的有效训练过程。学习过程涉及两个阶段。在第一阶段,训练一个粗粒度的生成模型,在一对一映射的简化框架下学习响应生成。在第二阶段,进一步训练细粒度生成模型和评估模型,分别学习不同的响应生成和响应一致性估计。PLATO-2采用中英文数据进行训练,通过综合评估验证其有效性和优越性,取得了最新的最新成果。
更新日期:2020-07-14
中文翻译:
PLATO-2:通过课程学习构建开放域聊天机器人
为了构建高质量的开放域聊天机器人,我们通过课程学习介绍了 PLATO-2 的有效训练过程。学习过程涉及两个阶段。在第一阶段,训练一个粗粒度的生成模型,在一对一映射的简化框架下学习响应生成。在第二阶段,进一步训练细粒度生成模型和评估模型,分别学习不同的响应生成和响应一致性估计。PLATO-2采用中英文数据进行训练,通过综合评估验证其有效性和优越性,取得了最新的最新成果。