# Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks

arXiv: https://arxiv.org/abs/2104.10193 · HTML: https://mlsanity.com/paper/2104.10193/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- ["Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding](https://mlsanity.com/paper/1909.03065/) (2019)
- [Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models](https://mlsanity.com/paper/2005.00683/) (2020)
- [Commonsense for Generative Multi-Hop Question Answering Tasks](https://mlsanity.com/paper/1809.06309/) (2018)
- [WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge](https://mlsanity.com/paper/2005.05763/) (2020)
- [Neural Natural Language Inference Models Enhanced with External Knowledge](https://mlsanity.com/paper/1711.04289/) (2017)
- [Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader](https://mlsanity.com/paper/1905.07098/) (2019)
- [Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/1910.14087/) (2019)
- [Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models](https://mlsanity.com/paper/1908.06725/) (2019)
- [MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants](https://mlsanity.com/paper/1905.09531/) (2019)
- [What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge](https://mlsanity.com/paper/1912.13337/) (2019)
- [Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering](https://mlsanity.com/paper/1911.03876/) (2019)
- [Why Do Masked Neural Language Models Still Need Common Sense Knowledge?](https://mlsanity.com/paper/1911.03024/) (2019)

## Built on by (most cited first, 9 of 9)

- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [On the Diversity of Synthetic Data and its Impact on Training Large Language Models](https://mlsanity.com/paper/2410.15226/) (2024)
- [A Systematic Investigation of Commonsense Knowledge in Large Language Models](https://mlsanity.com/paper/2111.00607/) (2021)
- [Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models](https://mlsanity.com/paper/2109.02837/) (2021)
- [Probing Script Knowledge from Pre-Trained Models](https://mlsanity.com/paper/2204.10176/) (2022)
- [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/2201.06230/) (2022)
- [Interactive Model with Structural Loss for Language-based Abductive Reasoning](https://mlsanity.com/paper/2112.00284/) (2021)
- [Text-To-KG Alignment: Comparing Current Methods on Classification Tasks](https://mlsanity.com/paper/2306.02871/) (2023)
- [A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity](https://mlsanity.com/paper/2506.17847/) (2025)

## Abstract (arXiv)

Integrating external knowledge into commonsense reasoning tasks has shown progress in resolving some, but not all, knowledge gaps in these tasks. For knowledge integration to yield peak performance, it is critical to select a knowledge graph (KG) that is well-aligned with the given task's objective. We present an approach to assess how well a candidate KG can correctly identify and accurately fill in gaps of reasoning for a task, which we call KG-to-task match. We show this KG-to-task match in 3 phases: knowledge-task identification, knowledge-task alignment, and knowledge-task integration. We also analyze our transformer-based KG-to-task models via commonsense probes to measure how much knowledge is captured in these models before and after KG integration. Empirically, we investigate KG matches for the SocialIQA (SIQA) (Sap et al., 2019b), Physical IQA (PIQA) (Bisk et al., 2020), and MCScript2.0 (Ostermann et al., 2019) datasets with 3 diverse KGs: ATOMIC (Sap et al., 2019a), ConceptNet (Speer et al., 2017), and an automatically constructed instructional KG based on WikiHow (Koupaee and Wang, 2018). With our methods we are able to demonstrate that ATOMIC, an event-inference focused KG, is the best match for SIQA and MCScript2.0, and that the taxonomic ConceptNet and WikiHow-based KGs are the best matches for PIQA across all 3 analysis phases. We verify our methods and findings with human evaluation.