2004 ConceptNet

From GM-RKB
Jump to: navigation, search

Subject Headings: ConceptNet, Common Sense Knowledge Base, ConceptNet Semantic Relation Ontology, Open Mind Common Sense Project.

Notes

Cited By

Quotes

Abstract

ConceptNet is a freely available commonsense knowledge base and natural-language-processing tool-kit which supports many practical textual-reasoning tasks over real-world documents including topic-gisting, analogy-making, and other context oriented inferences. The knowledge base is a semantic network presently consisting of over 1.6 million assertions of commonsense knowledge encompassing the spatial, physical, social, temporal, and psychological aspects of everyday life. ConceptNet is generated automatically from the 700 000 sentences of the Open Mind Common Sense Project — a World Wide Web based collaboration with over 14000 authors.

1. Introduction

In today’s digital age, text is the primary medium of representing and transmitting information, as evidenced by the pervasiveness of e-mails, instant messages, documents, weblogs, news articles, homepages, and printed materials. …

2. ConceptNet, Cyc, and WordNet

...

2.2 Structured like WordNet, relationally rich like Cyc

Secondly, we extend WordNet's repertoire of semantic relations from the triplet of synonym, is-a, and part-of, to a present repertoire of twenty semantic relations including, for example, EffectOf (causality), SubeventOf (event hierarchy), CapableOf (agent’s ability), PropertyOf, LocationOf, and MotivationOf (affect). Some further intuition for this relational ontology is given in the next section of the paper. Although ConceptNet increases the number and variety of semantic relations, engineering complexity is not necessarily increased.

ConceptNet as a context machine

Like WordNet, ConceptNet’s semantic network is amenable to context-friendly reasoning methods such as spreading activation [9] (think — activation radiating outward from an origin node) and graph traversal. However, since ConceptNet’s nodes and relational ontology are more richly descriptive of everyday commonsense than WordNet’s, better contextual commonsense inferences can be achieved, and require only simple improvements to spreading activation.

Structure of the ConceptNet knowledge base

The ConceptNet knowledge base is formed by the linking together of 1.6 million assertions (1.25 million of which are klines) into a semantic network of over 300 000 nodes. The present relational ontology consists of twenty relation-types.

Figure 2 is a treemap of the ConceptNet relational ontology, showing the relative amounts of knowledge falling under each relation-type. Table 1 gives a concrete example of each relation-type.

Table 1 ConceptNet’s twenty relation-types are illustrated by examples from actual ConceptNet data. The relation-types are grouped into various thematics. f counts the number of times a fact is uttered in the OMCS corpus. i counts how many times an assertion was inferred during the ‘relaxation’ phase.

  • K-LINES (1.25 million assertions)
    • (ConceptuallyRelatedTo ‘bad breath’ ‘mint’ ‘f=4;i=0;’)
    • (ThematicKLine ‘wedding dress’ ‘veil’ ‘f=9;i=0;’)
    • (SuperThematicKLine ‘western civilisation’ ‘civilisation’ ‘f=0;i=12;’)
  • THINGS (52 000 assertions)
    • (IsA ‘horse’ ‘mammal’ ‘f=17;i=3;’)
    • (PropertyOf ‘fire’ ‘dangerous’ ‘f=17;i=1;’)
    • (PartOf ‘butterfly’ ‘wing’ ‘f=5;i=1;’)
    • (MadeOf ‘bacon’ ‘pig’ ‘f=3;i=0;’)
    • (DefinedAs ‘meat’ ‘flesh of animal’ ‘f=2;i=1;’)
  • AGENTS (104 000 assertions)
    • (CapableOf ‘dentist’ ‘pull tooth’ ‘f=4;i=0;’)
  • EVENTS (38 000 assertions)
    • (PrerequisiteEventOf ‘read letter’ ‘open envelope’ ‘f=2;i=0;’)
    • (FirstSubeventOf ‘start fire’ ‘light match’ ‘f=2;i=3;’)
    • (SubeventOf ‘play sport’ ‘score goal’ ‘f=2;i=0;’)
    • (LastSubeventOf ‘attend classical concert’ ‘applaud’ ‘f=2;i=1;’)
  • SPATIAL (36 000 assertions)
    • (LocationOf ‘army’ ‘in war’ ‘f=3;i=0;’)
  • CAUSAL (17 000 assertions)
    • (EffectOf ‘view video’ ‘entertainment’ ‘f=2;i=0;’)
    • (DesirousEffectOf ‘sweat’ ‘take shower’ ‘f=3;i=1;’)
  • FUNCTIONAL (115 000 assertions)
    • (UsedFor ‘fireplace’ ‘burn wood’ ‘f=1;i =2;’)
    • (CapableOfReceivingAction ‘drink’ ‘serve’ ‘f =0;i =14;’)
  • AFFECTIVE (34 000 assertions)
    • (MotivationOf ‘play game’ ‘compete’ ‘f =3;i=0;’)
    • (DesireOf ‘person’ ‘not be depressed’ ‘f=2;i=0;’)

ConceptNet’s relational ontology was determined quite organically. The original OMCS corpus was built largely through its users filling in the blanks of templates like ‘a hammer is for ...’. Other portions of the OMCS corpus accepted freeform input, but restricted the length of the input so as to encourage pithy phrasing and simple syntax. ConceptNet's choice of relation-types reflect our original choice of templates in OMCS, and also reflect common patterns we observed in the freeform portion of the corpus.

Practical commonsense reasoning with the ConceptNet tool-kit

Whereas logic is microscopic, highly granular, well-defined, and static, context is macroscopic, gestalt, heuristic, nd quite dynamic. ConceptNet excels at problems of context because it is more invested in the many ways that commonsense concepts relate to one another, rather than obsessing over the truth conditions of particular assertions. By nuancing network-based reasoning methods such as spreading activation to take advantage of ConceptNet’s relational-ontology, various contextual-commonsense-reasoning tasks can be achieved.

References

  • 1. Liu H and Singh P: 'Commonsense Reasoning in and over Natural Language', Proceedings of the 8th International Conference on Knowledge-Based Intelligent Information and Engineering Systems (KES-2004) (2004).
  • 2. Marvin Minsky, The Society of Mind, Simon & Schuster, Inc., New York, NY, 1986
  • 3. Dreifus C: 'Got Stuck for a Moment: An Interview with Marvin Minsky', International Herald Tribune (August 1998).
  • 4. Fellbaum C (Ed): 'WordNet: An Electronic Lexical Database', MIT Press (1998).
  • 5. Douglas B. Lenat, CYC: A Large-scale Investment in Knowledge Infrastructure, Communications of the ACM, v.38 n.11, p.33-38, Nov. 1995 doi:10.1145/219717.219745
  • 6. Push Singh, Thomas Lin, Erik T. Mueller, Grace Lim, Travell Perkins, Wan Li Zhu, Open Mind Common Sense: Knowledge Acquisition from the General Public, On the Move to Meaningful Internet Systems, 2002 - DOA/CoopIS/ODBASE 2002 Confederated International Conferences DOA, CoopIS and ODBASE 2002, p.1223-1237, October 30-November 01, 2002
  • 7. Turner E: 'OMCSNet-WNLG Project', (2003) -- http:// Www.eturner.net/omcsnetcpp/wordnet
  • 8. David Gelernter, The Muse in the Machine: Computerizing the Poetry of Human Thought, The Free Press, New York, NY, 1994
  • 9. Collins A and Loftus E: 'A Spreading-activation Theory of Semantic Processing', Psychological Review, 82, No 6, Pp 407-428 (1975).
  • 10. Liu H and Lieberman H: 'Robust Photo Retrieval Using World Semantics', Proceedings of LREC2002 Workshop: Using Semantics for IR, Canary Islands, Pp 15-20 (2002).
  • 11. H. Lieberman, A. Faaborg, J. Espinosa, T. Stocky, Commonsense on the Go, BT Technology Journal, v.22 n.4, p.241-252, October 2004 doi:10.1023/B:BTTJ.0000047602.54693.3d
  • 12. Eagle N, Singh P and Pentland A: 'Common Sense Conversations: Understanding Casual Conversation Using a Common Sense Database', Proceedings of the Artificial Intelligence, Information Access, and Mobile Computing Workshop (IJCAI 2003) (2003).
  • 13. Commonsense Reasoning for Interactive Applications Projects (2003) -- http://www.media.mit.edu/~lieber/Teaching/Common-Sense-Course/Projects/Projects-Intro.html
  • 14. Liu H: 'MontyLingua V1.3.1', Toolkit and API (2003) -- http:// Web.media.mit.edu/~hugo/montylingua/
  • 15. Collin F. Baker, Charles J. Fillmore, John B. Lowe, The Berkeley FrameNet Project, Proceedings of the 17th International Conference on Computational Linguistics, August 10-14, 1998, Montreal, Quebec, Canada doi:10.3115/980451.980860
  • 16. Musa R, Scheidegger M, Kulas A and Anguilet Y: 'GloBuddy, a Dynamic Broad Context Phrase Book', in Proceedings of CONTEXT'2003, Pp 467-474, Springer (2003).
  • 17. David B. Leake, Case-Based Reasoning: Experiences, Lessons and Future Directions, MIT Press, Cambridge, MA, 1996
  • 18. Gentner D: 'Structure-mapping: A Theoretical Framework for Analogy', Cognitive Science, 7, Pp 155-170 (1983).
  • 19. Chalmers D J, French R M and Hofstadter D R: 'High-level Perception, Representation, and Analogy: A Critique of Artificial Intelligence Methodology', Technical Report CRCC-TR-49, Center for Research in Concepts and Cognition, Indiana University (March 1991).
  • 20. Douglas Hofstadter, Melanie Mitchell, The Copycat Project: A Model of Mental Fluidity and Analogy-making, Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought, Basic Books, Inc., New York, NY, 1995
  • 21. Hugo Liu, Push Singh, Makebelieve: Using Commonsense Knowledge to Generate Stories, Eighteenth National Conference on Artificial Intelligence, p.957-958, July 28-August 01, 2002, Edmonton, Alberta, Canada
  • 22. Wang A: 'Turn-taking in a Collaborative Storytelling Agent', Masters Thesis, MIT Department of Electrical Engineering and Computer Science (2002).
  • 23. Hovy E H and Lin C H: 'Automated Text Summarisation in SUMMARIST', Proceedings of the ACL97/EACL97 Workshop on Intelligent Scalable Text Summarisation, Madrid, Spain (July 1997).
  • 24. Hugo Liu, Henry Lieberman, Ted Selker, A Model of Textual Affect Sensing Using Real-world Knowledge, Proceedings of the 8th International Conference on Intelligent User Interfaces, January 12-15, 2003, Miami, Florida, USA doi:10.1145/604045.604067
  • 25. Lieberman H, Liu H, Singh P and Barry B: 'Beating Some Common Sense Into Interactive Applications', AI Magazine (to Appear in Fall 2004 Issue).
  • 26. Hugo Liu, Henry Lieberman, Ted Selker, GOOSE: A Goal-Oriented Search Engine with Commonsense, Proceedings of the Second International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, p.253-263, May 29-31, 2002
  • 27. Liu H: 'Unpacking Meaning from Words: A Context-centered Approach to Computational Lexicon Design', in Blackburn Et Al (Eds): 'Modeling and Using Context', 4th International and Interdisciplinary Conference (CONTEXT 2003) Proceedings, Lecture Notes in Computer Science No 2680, Springer, Pp 218- 232 (2003).
  • 28. Singh P and Williams W: 'LifeNet: A Propositional Model of Ordinary Human Activity', Proceedings of the Workshop on Distributed and Collaborative Knowledge Capture (DC-KCAP) at KCAP 2003, Sanibel Island, Florida (2003).
  • 29. Hugo Liu, Pattie Maes, What Would They Think?: A Computational Model of Attitudes, Proceedings of the 9th International Conference on Intelligent User Interfaces, January 13-16, 2004, Funchal, Madeira, Portugal doi:10.1145/964442.964451
  • 30. Tom Stocky, Alexander Faaborg, Henry Lieberman, A Commonsense Approach to Predictive Text Entry, CHI '04 Extended Abstracts on Human Factors in Computing Systems, April 24-29, 2004, Vienna, Austria doi:10.1145/985921.986014
  • 31. Ashwani Kumar, Sharad C. Sundararajan, Henry Lieberman, Common Sense Investing: Bridging the Gap Between Expert and Novice, CHI '04 Extended Abstracts on Human Factors in Computing Systems, April 24-29, 2004, Vienna, Austria doi:10.1145/985921.986015
  • 32. Hugo Liu, Henry Lieberman, Toward a Programmatic Semantics of Natural Language, Proceedings of the 2004 IEEE Symposium on Visual Languages - Human Centric Computing (VLHCC'04), p.281-282, September 26-29, 2004 doi:10.1109/VLHCC.2004.59
  • 33. Lieberman H and Liu H: 'Feasibility Studies for Programming in Natural Language', in Lieberman H, Paterno F and Wulf V (Eds): 'Perspectives in End-User Development', Kluwer (Summer 2004).,


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2004 ConceptNetHugo Liu
Push Singh
ConceptNet — A Practical Commonsense Reasoning Tool-Kithttp://web.media.mit.edu/~hugo/publications/papers/BTTJ-ConceptNet.pdf2004