Commonsense Knowledge in Word Associations and ConceptNet
Not on the map. Why?
Abstract (arXiv)
Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, understanding how commonsense knowledge is represented in different paradigms is important for both deeper understanding of human cognition and for augmenting automatic reasoning systems. This paper presents an in-depth comparison of two large-scale resources of general knowledge: ConcpetNet, an engineered relational database, and SWOW a knowledge graph derived from crowd-sourced word associations. We examine the structure, overlap and differences between the two graphs, as well as the extent to which they encode situational commonsense knowledge. We finally show empirically that both resources improve downstream task performance on commonsense reasoning benchmarks over text-only baselines, suggesting that large-scale word association data, which have been obtained for several languages through crowd-sourcing, can be a valuable complement to curated knowledge graphs
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 27 of its 60 references that are in the map. First posted on arXiv 20 Sep 2021.
Builds on
27 of 60 references.
References · 27
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
- 2016Gaussian Error Linear Units (GELUs)cited by 3,472
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,779
- 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,133
- 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,805
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 769
- 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
- 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 414
- 2017A simple neural network module for relational reasoningcited by 345
- 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
15 more
- 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
- 2018Constituency Parsing with a Self-Attentive Encodercited by 197
- 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
- 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
- 2018Modeling Naive Psychology of Characters in Simple Commonsense Storiescited by 60
- 2018Improving Natural Language Inference Using External Knowledge in the Science Questions Domaincited by 48
- 2020CSKG: The CommonSense Knowledge Graphcited by 45
- 2020Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answeringcited by 44
- 2020Fusing Context Into Knowledge Graph for Commonsense Question Answeringcited by 33
- 2021Relational World Knowledge Representation in Contextual Language Models: A Reviewcited by 31
- 2018MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledgecited by 30
- 2021Dimensions of Commonsense Knowledgecited by 29
- 2019Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representationscited by 24
- 2019MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participantscited by 20
- 2020Consolidating Commonsense Knowledgecited by 5
Built on by
Citing papers per year: 2025: 2.
2 papers.