ConceptNet 3 : a Flexible , Multilingual Semantic Network for Common Sense Knowledge

By Catherine Havasi, Jason B. Alonso. 2007

320 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b1efe271962d723069b095b45d1c623a8a5443c1

How researchers see this paper

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

Citations in the corpus

Extracting implicit knowledge from text (2009, background): “) explains that Havasi et al. (2007) should be interpreted as saying merely that we shouldn’t expect to acquire all common knowledge from text.”
Reporting bias and knowledge acquisition (2013, background): “[19] previously knowledge acquisition from text to Gricean principles, noting that “people tend not to provide information which is obvious or extraneous” and, therefore, “it is difficult to automatically extract common-sense statements from text, and the results tend to be unreliable”.”
Representing General Relational Knowledge in ConceptNet 5 (2012, methodology): “ConceptNet 3 (Havasi et al., 2007) made ConceptNet into a SQL database, so it could be easily updated by processes including user interaction from a Web site.”
SenticNet: A Publicly Available Semantic Resource for Opinion Mining (2010, background): “ConceptNet (Havasi, Speer, and Alonso 2007) represents the information in the Open Mind corpus as a directed graph in which the nodes are concepts and the labelled edges are assertions of common sense that interconnect them.”
What Does My QA Model Know? Devising Controlled Probes Using Expert Knowledge (2019, methodology): “Our main motivation for using WordNet, as opposed to a resource such as ConceptNet (Havasi et al., 2007), is the availability of glosses (D) and example sentences (S), which allows us to construct natural language questions that contextualize the types of concepts we want to probe.”
Grounding Robot Plans from Natural Language Instructions with Incomplete World Knowledge (2018, methodology): “For the MLN M wL,C , we use predicates indicating whether words are associated with syntactic and semantic labels like part of speech tags, dependency relations, Wordnet [14] synsets, ConceptNet relations [15], and Framenet [16] actions and roles.”
Conversational Neuro-Symbolic Commonsense Reasoning (2020, background): “Projects like CYC [7], ConceptNet [8–10] and ATOMIC [11, 12] are examples of such KBs (see [2] for a comprehensive list).”
The Limitations of Standardized Science Tests as Benchmarks for Artificial Intelligence Research: Position Paper (2014, methodology): “Ohlsson et al. (2013) evaluated the performance ConceptNet system (Havasi, Speer, and Alonso 2007) on a preprocessed form of the Wechesler Preschool and Primary Scale of Intelligence test.”
SemEval-2020 Task 4: Commonsense Validation and Explanation (2020, background): “ConceptNet is a seminal knowledge graph that has been upgraded over time (Liu and Singh, 2004; Havasi et al., 2007; Speer and Havasi, 2013; Speer et al., 2017).”
Coarse Word-Sense Disambiguation Using Common Sense (2010, methodology): “To make the knowledge in the OMCS corpus accessible to AI applications and machine learning techniques, we transform it into a semantic network called ConceptNet (Havasi, Speer, and Alonso 2007).”
How to Write Science Questions that Are Easy for People and Hard for Computers (2016, methodology): “These headlines are of course absurd; a four-year old can make up stories, chat, occasionally follow directions, invent words, learn language at an incredible pace; ConceptNet (the AI system in question) can do none of these.”
Learning Knowledge Graphs for Question Answering through Conversational Dialog (2015, background): “Relations can be intuitively arranged as a knowledge graph, which in this work is any graph whose nodes are concepts and whose edges are relations between those concepts, in the spirit of semantic networks such as ConceptNet (Havasi et al., 2007).”
Thinking Like a Skeptic: Defeasible Inference in Natural Language (2020, background): “Similarly, knowledge graphs for commonsense reasoning like ATOMIC (Sap et al., 2019) or ConceptNet (Havasi et al., 2007; Speer et al., 2017) encode inference rules about generic situations, but do not elaborate on possible exceptions to the applications of those rules.”
Ordinal Common-sense Inference (2016, background): “Efforts have pursued volunteers (Singh, 2002; Havasi et al., 2007) and games with a purpose (Chklovski, 2003), but are still left fully reliant on human labor.”
AffectiveSpace: Blending Common Sense and Affective Knowledge to Perform Emotive Reasoning (2009, background): “ConceptNet [8] represents the information in the Open Mind corpus as a directed graph in which the nodes are concepts and the labeled edges are assertions of Common Sense that interconnect them (Fig.”