# Learning Contextualized Knowledge Structures for Commonsense Reasoning

arXiv: https://arxiv.org/abs/2010.12873 · HTML: https://mlsanity.com/paper/2010.12873/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge](https://mlsanity.com/paper/2101.00376/) (2021)
- [PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales](https://mlsanity.com/paper/2211.01562/) (2022)
- [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)
- [Edge: Enriching Knowledge Graph Embeddings with External Text](https://mlsanity.com/paper/2104.04909/) (2021)
- [A Review on Knowledge Graphs for Healthcare: Resources, Applications, and Promises](https://mlsanity.com/paper/2306.04802/) (2023)
- [Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks](https://mlsanity.com/paper/2311.05085/) (2023)
- [AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension](https://mlsanity.com/paper/2203.08992/) (2022)
- [SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning](https://mlsanity.com/paper/2104.08793/) (2021)
- [Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/2305.08135/) (2023)
- [Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification](https://mlsanity.com/paper/2305.05921/) (2023)
- [CoSe-Co: Text Conditioned Generative CommonSense Contextualizer](https://mlsanity.com/paper/2206.05706/) (2022)
- [Diagnosing and Mitigating Semantic Inconsistencies in Wikidata's Classification Hierarchy](https://mlsanity.com/paper/2511.04926/) (2025)
- [Transfer Learning for Multi-lingual Tasks -- a Survey](https://mlsanity.com/paper/2110.02052/) (2021)
- [Differentiating Choices via Commonality for Multiple-Choice Question Answering](https://mlsanity.com/paper/2408.11554/) (2024)
- [Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering](https://mlsanity.com/paper/2408.12979/) (2024)

## Abstract (arXiv)

Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for the subgraph's missing edges to form a "hybrid" graph, then reason over the hybrid graph while filtering out context-irrelevant edges. We demonstrate HGN's effectiveness through considerable performance gains across four commonsense reasoning benchmarks, plus a user study on edge validness and helpfulness.