# Incremental Knowledge Based Question Answering

arXiv: https://arxiv.org/abs/2101.06938 · HTML: https://mlsanity.com/paper/2101.06938/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 18 Jan 2021.

## Builds on (most cited first, 18 of 18)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (2017)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases](https://mlsanity.com/paper/1606.01994/) (2016)
- [Simple Question Answering by Attentive Convolutional Neural Network](https://mlsanity.com/paper/1606.03391/) (2016)
- [Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks](https://mlsanity.com/paper/1712.01969/) (2017)
- [Incremental Learning from Scratch for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1906.04991/) (2019)
- [Character-Level Question Answering with Attention](https://mlsanity.com/paper/1604.00727/) (2016)
- [Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering](https://mlsanity.com/paper/1907.07328/) (2019)
- [Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model](https://mlsanity.com/paper/1808.07624/) (2018)
- [Question Answering over Knowledge Base with Neural Attention Combining Global Knowledge Information](https://mlsanity.com/paper/1606.00979/) (2016)

## Built on by (most cited first, 1 of 1)

- [Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices](https://mlsanity.com/paper/2112.03572/) (2021)

## Abstract (arXiv)

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.