# Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

arXiv: https://arxiv.org/abs/2011.02705 · HTML: https://mlsanity.com/paper/2011.02705/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 14 of 14)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering](https://mlsanity.com/paper/2112.02732/) (2021)
- [Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention](https://mlsanity.com/paper/2112.03254/) (2021)
- [DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning](https://mlsanity.com/paper/2208.00635/) (2022)
- [Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2305.08135/) (2023)
- [Natural Language Processing with Commonsense Knowledge: A Survey](https://mlsanity.com/paper/2108.04674/) (2021)
- [KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering](https://mlsanity.com/paper/2305.08347/) (2023)
- [Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links](https://mlsanity.com/paper/2309.05201/) (2023)
- [Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts](https://mlsanity.com/paper/2201.02740/) (2021)
- [Rethinking the Value of Gazetteer in Chinese Named Entity Recognition](https://mlsanity.com/paper/2207.02802/) (2022)
- [Large Language Models Are Also Good Prototypical Commonsense Reasoners](https://mlsanity.com/paper/2309.13165/) (2023)
- [UFO: Unified Fact Obtaining for Commonsense Question Answering](https://mlsanity.com/paper/2305.16048/) (2023)
- [CASE: Commonsense-Augmented Score with an Expanded Answer Space](https://mlsanity.com/paper/2311.01684/) (2023)
- [Differentiating Choices via Commonality for Multiple-Choice Question Answering](https://mlsanity.com/paper/2408.11554/) (2024)

## Abstract (arXiv)

In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research academia and industry. In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance. More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources. Afterward, we use a pre-trained language model to encode the question, retrieved knowledge and choices, and propose an answer choice-aware attention mechanism to fuse all hidden representations of the previous modules. Finally, the linear classifier for specific tasks is used to predict the answer. Experimental results on the CommonsenseQA dataset show that our method significantly outperforms other competitive methods and achieves the new state-of-the-art. In addition, further ablation studies demonstrate the effectiveness of our graph-based iterative knowledge retrieval module and the answer choice-aware attention module in retrieving and synthesizing background knowledge from multiple knowledge sources.