ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources

TL;DR

ADMUS is a flexible, multi-stage KBQA framework that simplifies adapting to various datasets, languages, and knowledge bases, reducing integration costs and supporting progressive question answering methods.

Contribution

It introduces a dataset-independent, micro-service-based architecture for KBQA, enabling easy integration of new datasets and supporting progressive answering stages.

Findings

Supports multiple languages and knowledge bases

Facilitates quick dataset integration with micro-services

Implements a three-stage progressive answering process

Abstract

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