Incremental Knowledge Based Question Answering

by   Yongqi Li, et al.

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.


page 1

page 2

page 3

page 4


Question Answering over Knowledge Base using Language Model Embeddings

Knowledge Base, represents facts about the world, often in some form of ...

Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end

In this work we propose a system for visual question answering. Our arch...

A Two-Stage Approach towards Generalization in Knowledge Base Question Answering

Most existing approaches for Knowledge Base Question Answering (KBQA) fo...

An Incremental Learning framework for Large-scale CTR Prediction

In this work we introduce an incremental learning framework for Click-Th...

Anti-Retroactive Interference for Lifelong Learning

Humans can continuously learn new knowledge. However, machine learning m...

Random Path Selection for Incremental Learning

Incremental life-long learning is a main challenge towards the long-stan...

Ask Me What You Need: Product Retrieval using Knowledge from GPT-3

As online merchandise become more common, many studies focus on embeddin...