Incremental Knowledge Based Question Answering

Abstract

In the past years, Knowledge-Based Question Answering (KBQA), which aims to answer natural language questions using facts in a knowledge base, has been well developed. Existing approaches often assume a static knowledge base. However, the knowledge is evolving over time in the real world. If we directly apply a fine-tuning strategy on an evolving knowledge base, it will suffer from a serious catastrophic forgetting problem. In this paper, we propose a new incremental KBQA learning framework that can progressively expand learning capacity as humans do. Specifically, it comprises a margin-distilled loss and a collaborative exemplar selection method, to overcome the catastrophic forgetting problem by taking advantage of knowledge distillation. We reorganize the SimpleQuestion dataset to evaluate the proposed incremental learning solution to KBQA. The comprehensive experiments demonstrate its effectiveness and efficiency when working with the evolving knowledge base.

Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices

“…Multiple predicates are required to constrain the answer set for such questions complex questions, if the knowledge graph is used [42,67,8]. To tackle this problem Luo et al [71], first generate multiple query graphs for a given question.…”

Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices

“…Multiple predicates are required to constrain the answer set for such questions complex questions, if the knowledge graph is used [42,66,8]. To tackle this problem Luo et al [70], first generate multiple query graphs for a given question.…”