ConceptNet — A Practical Commonsense Reasoning Tool-Kit

By Hugo Liu, Push Singh. 2004

781 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Knowledge Graphs & Representation

Citations in the corpus

KAT: A Knowledge Augmented Transformer for Vision-and-Language (2021, background): “, 2007) and ConceptNet (Liu and Singh, 2004) before jointly reasoning over the retrieved knowledge and image content to predict an answer.”
Commonsense Knowledge Mining from Pretrained Models (2019, methodology): “These works use relations from ConceptNet, a crowd-sourced database of structured commonsense knowledge, to train and validate their models (Liu and Singh, 2004).”
A Survey on Hate Speech Detection using Natural Language Processing (2017, background): “The basis of their model is the general-purpose ontology ConceptNet (Liu and Singh, 2004), which encodes concepts that are connected by relations to form assertions, such as “a skirt is a form of female attire” .”
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (2019, background): “ConceptNet is a prestigious knowledge graph that has been up-graded over a long time (Liu and Singh, 2004; Havasi et al., 2007; Speer and Havasi, 2013; Speer et al., 2017).”
Representing General Relational Knowledge in ConceptNet 5 (2012, background): “The ﬁrst publicly released version of ConceptNet was Con-ceptNet 2 (Liu and Singh, 2004).”
FVQA: Fact-Based Visual Question Answering (2016, methodology): “, YAGO [28, 33], OpenIE [24, 34, 35], NELL [26], NEIL [27, 36], WebChild [37,38], ConceptNet [39]).”
Distributional Memory: A General Framework for Corpus-Based Semantics (2010, neutral): “This is customary in lexical networks like WordNet (Fellbaum 1998), commonsense resources like ConceptNet (Liu and Singh 2004), and cognitive models of semantic memory (Rogers and McClelland 2004).”
Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation (2021, positive): “In RG, several works have tried to incorporate commonsense (Zhou et al., 2018; Zhang et al., 2020a) using ConceptNet, a common-sense knowledge graph (Liu and Singh, 2004) to make responses more natural-sounding.”
CVBed: Structuring CVs usingWord Embeddings (2017, methodology): “While WordNet and Concept-Net are valuable lexical resources on their own, but clearly a predeﬁned knowledge representation proves to be inadequate to capture the intricacies that CVs tend to present in real life.”
Deriving a Web-Scale Common Sense Fact Database (2011, background): “Liu and Singh (2004) provide a survey of applications that have made use of explicit common sense facts.”
A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge (2018, background): “Other work aims to develop a repository of common-sense knowledge (e.g., Cyc (Lenat, 1995), ConceptNet (Liu and Singh, 2004)) using semi-automatic methods.”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, background): “The ﬁrst challenge is the scale and incomplete nature of KGs. Real-world KGs (Bollacker et al., 2008; Suchanek et al., 2007; Liu & Singh, 2004) often have millions of entities, and multi-hop traversal on a KG leads to an exponential growth in computation time and space.”
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning (2021, methodology): “Given that our training data is not sufﬁcient to learn commonsense relations be-tween concepts from scratch, we initially ﬁne-tune the RoBERTa pre-trained weights and the edge clas-siﬁer on ConceptNet (Liu and Singh, 2004) triples.”
Relational World Knowledge Representation in Contextual Language Models: A Review (2021, background): “Examples include the publicly accessible, crowdsourced resources ConceptNet (Liu and Singh, 2004; Speer et al., 2017) and ATOMIC (Sap et al.”
What Can You Do with a Rock? Affordance Extraction via Word Embeddings (2017, methodology): “ConceptNet reduction: In this approach we used ConceptNet’s CapableOf relation to obtain a list of verbs relevant to the current object.”
Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning (2021, neutral): “More specifically, their proposed method uses 4 layers LSTM with running expected average on ConceptNet [27] concepts for each word produced in the caption, which it introduces a significant computation overload.”
Explaining Toxic Text via Knowledge Enhanced Text Generation (2022, background): “, 2017), since it contains commonsense knowledge (Liu and Singh, 2004).”
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020, background): “, 2019), reasoning (Schubert, 2015), property (Liu and Singh, 2004), and quantity (Elazar et al.”
Metaphoria: An Algorithmic Companion for Metaphor Creation (2019, methodology): “To find features of the vehicle we use ConceptNet [24], an open-source knowledge graph, as a source of structural and functional properties of words.”