CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System
This work addresses the problem of improving performance in information-seeking dialogue systems for users needing accurate and fluent responses, but it appears incremental as it applies existing methods to a specific competition.
The paper tackled the challenge of information-seeking dialogue systems by using data augmentation and training techniques with pre-trained language models, achieving a 74.95 F1 score and 60.74 Exact Match in subtask 1 and a 37.72 SacreBLEU score in subtask 2 of the DialDoc21 competition.
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.