ConceptNet

Notes:

ConceptNet is a large-scale, open-source semantic network that represents common-sense knowledge about the world. It is a collection of interconnected concepts and relationships between them, and is designed to be used in natural language processing tasks such as language translation, information retrieval, and question answering.

ConceptNet is created and maintained by the Open Mind Common Sense project, which is a collaboration between researchers at the Massachusetts Institute of Technology (MIT) Media Lab and other institutions. The network is built using a combination of automated methods and human contributions, and is available in multiple languages.

ConceptNet is used in a variety of applications, such as:

  • Natural language processing: ConceptNet can be used to improve the understanding of natural language by providing a context for words and phrases. For example, a language translation system might use ConceptNet to determine the appropriate translation for a word or phrase based on its relationships with other concepts in the network.
  • Information retrieval: ConceptNet can be used to improve the accuracy of search engines and other information retrieval systems by providing additional context and meaning for search terms.
  • Question answering: ConceptNet can be used to answer questions by using the relationships between concepts in the network to determine the most appropriate response.
  • Robotics and artificial intelligence: ConceptNet can be used to provide common-sense knowledge to robots and artificial intelligence systems, helping them to better understand and interact with their environment.

Resources:

Wikipedia:

See also:

MindNet | NLTK & Chatbots | Semantic Networks & Dialog Systems

Representing General Relational Knowledge in ConceptNet 5.
R Speer, C Havasi – LREC, 2012 – lrec-conf.org
ConceptNet is a knowledge representation project, providing a large semantic graph that describes general human knowledge and how it is expressed in natural language. This paper presents the latest iteration, ConceptNet 5, including its fundamental design …

ConceptNet 5: A large semantic network for relational knowledge
R Speer, C Havasi – The People’s Web Meets NLP, 2013 – Springer
ConceptNet is a knowledge representation project, providing a large semantic graph that describes general human knowledge and how it is expressed in natural language. Here we present the latest iteration, ConceptNet 5, with a focus on its fundamental design decisions …

Combining WordNet and ConceptNet for automatic query expansion: a learning approach
MH Hsu, MF Tsai, HH Chen – Asia information retrieval symposium, 2008 – Springer
We present a novel approach that transforms the weighting task to a typical coarse-grained classification problem, aiming to assign appropriate weights for candidate expansion terms, which are selected from WordNet and ConceptNet by performing spreading activation. This …

ConceptNet 5.5: An Open Multilingual Graph of General Knowledge.
R Speer, J Chin, C Havasi – AAAI, 2017 – aaai.org
Abstract Machine learning about language can be improved by supplying it with specific knowledge and sources of external information. We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be used with modern NLP …

Tapping into knowledge base for concept feedback: leveraging conceptnet to improve search results for difficult queries
A Kotov, CX Zhai – Proceedings of the fifth ACM international conference …, 2012 – dl.acm.org
Query expansion is an important and commonly used technique for improving Web search results. Existing methods for query expansion have mostly relied on global or local analysis of document collection, click-through data, or simple ontologies such as WordNet. In this …

Sentiment aggregation using ConceptNet ontology
S Mukherjee, S Joshi – Proceedings of the Sixth International Joint …, 2013 – aclweb.org
Sentiment analysis of reviews traditionally ignored the association between the features of the given product domain. The hierarchical relationship between the features of a product and their associated sentiment that influence the polarity of a review is not dealt with very …

Diversified query expansion using conceptnet
A Bouchoucha, J He, JY Nie – … of the 22nd ACM international conference …, 2013 – dl.acm.org
Search result diversification (SRD) aims to select diverse documents from the search results in order to cover as many search intents as possible. A prerequisite is that the search results contain diverse documents. For this purpose, we investigate a new approach to SRD by …

Using relation selection to improve value propagation in a conceptnet-based sentiment dictionary
CE Wu, RTH Tsai – Knowledge-Based Systems, 2014 – Elsevier
Sentiment analysis has become an important topic in natural language processing in recent years, and sentiment dictionaries are essential for research in this field. Concept-level sentiment dictionaries have broader coverage than word-based dictionaries, but they are …

Conceptnet at semeval-2017 task 2: Extending word embeddings with multilingual relational knowledge
R Speer, J Lowry-Duda – arXiv preprint arXiv:1704.03560, 2017 – arxiv.org
This paper describes Luminoso’s participation in SemEval 2017 Task 2,” Multilingual and Cross-lingual Semantic Word Similarity”, with a system based on ConceptNet. ConceptNet is an open, multilingual knowledge graph that focuses on general knowledge that relates the …

Combining conceptnet and wordnet for word sense disambiguation
J Chen, J Liu – Proceedings of 5th International Joint Conference on …, 2011 – aclweb.org
Abstract Knowledge-based Word sense Disambiguation (WSD) methods heavily depend on knowledge. Therefore enriching knowledge is one of the most important issues in WSD. This paper proposes a novel idea of combining WordNet and ConceptNet for WSD. First, we …

Edge dependent pathway scoring for calculating semantic similarity in ConceptNet
S Spagnola, C Lagoze – … of the Ninth International Conference on …, 2011 – dl.acm.org
Most techniques that calculate the relatedness between two concepts use a semantic network, such as Wikipedia, WordNet, or ConceptNet, to find the shortest intermediate pathway between two nodes. These techniques assume that a low number of edges on the …

Automating fictional ideation using ConceptNet
M Llano, R Hepworth, S Colton… – Proceedings of the …, 2014 – ccg.doc.gold.ac.uk
The invention of fictional ideas (ideation) is often a central process in producing artefacts such as poems, music and paintings in a creative way. Automated fictional ideation should, therefore, be of much interest in the study of Computational Creativity, but only a few …

Conceptnet 5
R Speer, C Havasi – Tiny Transactions of Computer …, 2012 – pdfs.semanticscholar.org
ConceptNet is a knowledge representation project, providing a large semantic graph that describes general human knowledge and how it is expressed in natural language. The scope of ConceptNet includes words and common phrases in any written human language …

Towards an RDF encoding of ConceptNet
M Grassi, F Piazza – International Symposium on Neural Networks, 2011 – Springer
The possibility of relying on a rich background knowledge constitutes a key element for the development of more effective sentiment analysis and SW applications. In this paper, we propose to encode the wide knowledge base collected by Open Mind Common Sense …

Extracting conceptnet knowledge triplets from japanese wikipedia
M Krawczyk, R Rzepka, K Araki – … of the 21st …, 2015 – arakilab.media.eng.hokudai.ac.jp
This paper presents a method of acquiring IsA assertions (hyponymy relations) AtLocation assertions (informing of location of objects) and LocatedNear assertions (informing of neighboring locations) automatically from Japanese Wikipedia XML dump files. To extract …

ConceptOnto: An upper ontology based on Conceptnet
E Najmi, K Hashmi, Z Malik, A Rezgui… – … (AICCSA), 2014 IEEE …, 2014 – ieeexplore.ieee.org
The exponential growth of information has prompted the introduction of new technologies such as Semantic Web and Common Sense knowledge bases. To connect the different knowledge presentations together is a primary requirement, and ontologies are central we …

Commonsense reasoning and large network analysis: A computational study of conceptnet 4
DI Diochnos – arXiv preprint arXiv:1304.5863, 2013 – arxiv.org
In this report a computational study of ConceptNet 4 is performed using tools from the field of network analysis. Part I describes the process of extracting the data from the SQL database that is available online, as well as how the closure of the input among the assertions in the …

Generality evaluation of automatically generated knowledge for the Japanese ConceptNet
R Rzepka, K Muramoto, K Araki – Australasian Joint Conference on …, 2011 – Springer
In this paper we introduce three methods for automatic generality evaluation of commonsense statements candidates generated for Open Mind Common Sense (OMCS), which is the basis of ConceptNet, a commonsense knowledge base. By using sister terms …

A Japanese Natural Language Toolset Implementation for ConceptNet.
TM Roberts, R Rzepka, K Araki – AAAI Fall Symposium: Commonsense …, 2010 – aaai.org
In recent years, ConceptNet has gained notoriety in the Natural Language Processing (NLP) as a textual commonsense knowledge base (CSKB) for its utilization of k-lines (Liu and Sing, 2004a) which make it suitable for making practical inferences on corpora (Liu and Sing …

An empirical comparison of statistical term association graphs with dbpedia and conceptnet for query expansion
R Anand, A Kotov – Proceedings of the 7th Forum for Information …, 2015 – dl.acm.org
Term graphs constructed from document collections as well as external resources, such as encyclopedias (DBpedia) and knowledge bases (ConceptNet), can be used as sources of semantically related terms for query expansion. Although these resources individually have …

ConceptRDF: An RDF presentation of ConceptNet knowledge base
E Najmi, Z Malik, K Hashmi… – … Systems (ICICS), 2016 …, 2016 – ieeexplore.ieee.org
The exponential growth of information on the Web has prompted the introduction of new technologies such as Semantic Web and Common Sense knowledge bases. While there are different models available to present information, RDF, as the cornerstone of Semantic Web …

Sentiment analysis using conceptnet ontology and context information
B Agarwal, N Mittal – Prominent Feature Extraction for Sentiment Analysis, 2016 – Springer
Sentiment analysis research has been increasing tremendously in recent times due to the wide range of business and social applications. Sentiment analysis from unstructured natural language text has recently received considerable attention from the research …

Populating ConceptNet Knowledge Base with Information Acquired from Japanese Wikipedia
M Krawczyk, R Rzepka, K Araki – Systems, Man, and …, 2015 – ieeexplore.ieee.org
This paper presents a method of acquiring IsA assertions (hyponymy relations), AtLocation assertions (informing of location of objects) and Located Near assertions (informing of neigh boring locations) automatically from Japanese Wikipedia XML dump files. To extract IsA …

Automatic evaluation of commonsense knowledge for refining japanese conceptnet
S Shudo, R Rzepka, K Araki – Proceedings of the 12th Workshop on …, 2016 – aclweb.org
In this paper we present two methods for automatic common sense knowledge evaluation for Japanese entries in ConceptNet ontology. Our proposed methods utilize text-mining approach, which is inspired by related research for evaluation of generality on natural …

Topic-aware sentiment prediction for Chinese ConceptNet
PH Chou, RTH Tsai, JY Hsu – Technologies and Applications …, 2015 – ieeexplore.ieee.org
Sentiment dictionary is a valuable resource in sentiment analysis research. Previous works propagate sentiment values from existing high quality dictionary on semantic networks to build wide coverage dictionary efficiently. But this approach suffers from quality degradation …

Extracting location and creator-related information from Wikipedia-based information-rich taxonomy for ConceptNet expansion
M Krawczyk, R Rzepka, K Araki – Knowledge-Based Systems, 2016 – Elsevier
Our research goal is to generate new assertions suitable for introduction to the Japanese part of the ConceptNet common sense knowledge ontology. In this paper we present a method for extracting IsA assertions (hyponymy relations), AtLocation assertions (informing …

Context-aware sentiment propagation using LDA topic modeling on Chinese ConceptNet
PH Chou, RTH Tsai, JY Hsu – Soft Computing, 2017 – Springer
A sentiment dictionary is a valuable resource in sentiment analysis research. Previous work has propagated sentiment values from existing dictionaries via semantic networks to build wide-coverage dictionaries efficiently. Unfortunately, this blind propagation method tends to …

A Semantic Approach to Enhance HITS Algorithm for Extracting Associated Concepts using ConceptNet
M Alsoos, A Kheirbek – Journal of Digital Information Management, 2015 – dline.info
Common sense knowledge base creation and usage is an active field of research, many researches in this field are trying to invent new methods to make machines more intelligent. ConceptNet is one of the most popular freely available common sense knowledge bases …

Automatic Detection of Off-topic Documents using ConceptNet and Essay Prompt in Automated English Essay Scoring
KJ Lee, GH Lee – Journal of KIISE, 2015 – koreascience.or.kr
This work presents a new method that can predict, without the use of training data, whether an input essay is written on a given topic. ConceptNet is a common-sense knowledge base that is generated automatically from sentences that are extracted from a variety of document …

Exploiting Wikipedia-Based Information-Rich Taxonomy for Extracting Location, Creator and Membership Related Information for ConceptNet Expansion
M Krawczyk, R Rzepka, K Araki – Language and Technology Conference, 2015 – Springer
In this paper we present a method for extracting IsA assertions (hyponymy relations), AtLocation assertions (informing of the location of an object or place), LocatedNear assertions (informing of neighboring locations), CreatedBy assertions (informing of the …

Folksonomy based Personalized Search using ConceptNet
R Sujatha – researchgate.net
The amount of information on the web is increasing day by day at an exponential rate. There is a need for retrieving the necessary information required for the user. The requirement of the information varies from user to user (example: variation in the required information …

Graph Based Sentiment Aggregation using ConceptNet Ontology
S Tamilselvam, S Nagar, A Mishra, K Dey – Proceedings of the Eighth …, 2017 – aclweb.org
The sentiment aggregation problem accounts for analyzing the sentiment of a user towards various aspects/features of a product, and meaningfully assimilating the pragmatic significance of these features/aspects from an opinionated text. The current paper addresses …

Introduction to WordNet, HowNet, FrameNet and ConceptNet
Z Lin – 2017 – tianjun.me
WordNet does not apply componential semantics It is assumed that the user already has the concept, and that meaning can be represented by any symbols that makes it possible to distinguish among them. Thus they concluded that it (componential semantics) was not the …

A Japanese Natural Language Toolset Implementation for ConceptNet
MR Tyson, R Rafal, A Kenji – … Knowledge, Papers from the …, 2010 – eprints.lib.hokudai.ac.jp
In recent years, ConceptNet has gained notoriety in the Natural Language Processing (NLP) as a textual commonsense knowledge base (CSKB) for its utilization of k-lines (Liu and Sing, 2004a) which make it suitable for making practical inferences on corpora (Liu and Sing …

A Concise Conversion Model for Improving the RDF Expression of ConceptNet Knowledge Base
H Chen, A Trouve, KJ Murakami, A Fukuda – Artificial Intelligence and …, 2018 – Springer
With the explosive growth of information on the Web, Semantic Web and related technologies such as linked data and commonsense knowledge bases, have been introduced. ConceptNet is a commonsense knowledge base, which is available for public …

Application of the semantic network ConceptNet
VD Tran – 2016 – repositories.lib.utexas.edu
This report introduces a way to use the semantic network ConceptNet to create a tool to aid in a writer’s creative process. ConceptNet is a project that maps concepts and their relationship to each other. The goal is to mimic our own creative search process of semantic …

Improvement of English-Hindi machine translation using ConceptNet
M Bansal, G Jain – Control, Automation & Power Engineering …, 2017 – ieeexplore.ieee.org
The paper is based on the framework of translation of English sentences into Hindi language by using ConceptNet for Statistical Machine Translation and Rule-Based Machine Translation system together. ConceptNet is a knowledge-based graph that represents …

ConceptNet: A lexical resource for common sense knowledge 1 Index of Subjects and Terms 13
C Havasi, R Speer, J Alonso – Citeseer
Abstract The Open Mind Common Sense project has been collecting commonsense knowledge from volunteers on the Internet since 2000. This knowledge is represented in a machine-interpretable semantic network called ConceptNet. We present ConceptNet 3 …

Ontology matching by using ConceptNet
V Kachitvichyanukul, HT Luong, R Pitakaso – disi.unitn.it
Ontology matching is a main step for integrating overlapping domains of knowledge and establishing interoperation among semantic web application. As information sources grow rapidly, manual ontology matching becomes more tedious and time-consuming and …

Rule-based Approach to Extracting Location, Creator and Membership-related Information from Wikipedia-based Information-rich Taxonomy for ConceptNet …
K Marek, R Rafal, A Kenji – Proceedings of Language …, 2016 – eprints.lib.hokudai.ac.jp
In this paper we present a method for extract-ing IsA assertions (hyponymy relations), AtLoca-tion assertions (informing of the location of an object or place), LocatedNear assertions (informing of neighboring locations), CreatedBy asser-tions (informing of the …