ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources
This work addresses the problem of dataset adaptability for KBQA systems in multi-tenant platforms, representing an incremental improvement by decoupling conventional architectures.
The authors tackled the high adaptation costs of knowledge base question answering (KBQA) systems across disparate datasets in real-world scenarios by proposing ADMUS, a progressive framework that supports seamless integration of new datasets with minimal effort, requiring only a dataset-related micro-service at negligible cost.
With the introduction of deep learning models, semantic parsingbased knowledge base question answering (KBQA) systems have achieved high performance in handling complex questions. However, most existing approaches primarily focus on enhancing the model's effectiveness on individual benchmark datasets, disregarding the high costs of adapting the system to disparate datasets in real-world scenarios (e.g., multi-tenant platform). Therefore, we present ADMUS, a progressive knowledge base question answering framework designed to accommodate a wide variety of datasets, including multiple languages, diverse backbone knowledge bases, and disparate question answering datasets. To accomplish the purpose, we decouple the architecture of conventional KBQA systems and propose this dataset-independent framework. Our framework supports the seamless integration of new datasets with minimal effort, only requiring creating a dataset-related micro-service at a negligible cost. To enhance the usability of ADUMS, we design a progressive framework consisting of three stages, ranges from executing exact queries, generating approximate queries and retrieving open-domain knowledge referring from large language models. An online demonstration of ADUMS is available at: https://answer.gstore.cn/pc/index.html