Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which. To tackle this challenge, we utilize data augmentation methods and several training techniques with the pre-trained language models to learn a general pattern of the task and thus achieve promising performance. In DialDoc21 competition, our system achieved 74.95 F1 score and 60.74 Exact Match score in subtask 1, and 37.72 SacreBLEU score in subtask 2. Empirical analysis is provided to explain the effectiveness of our approaches.
翻译：信息搜索对话系统,包括知识识别和回应生成,旨在根据用户的需要,以流利、一致和内容丰富的回应方式对用户作出反应。为了应对这一挑战,我们利用数据增强方法和若干培训技术以及预先培训的语言模式学习任务的一般模式,从而取得有希望的业绩。在拨号Doc21竞争中,我们的系统取得了74.95 F1分和60.74分,在子任务1和37.72 SaclebleU分,在子任务2中,我们提供了经验分析,以解释我们方法的有效性。
相关内容
微信扫码咨询专知VIP会员