SlideShare a Scribd company logo
ConceptNet - a pratical
commonsense reasoning
tool-kit
H Liu and P Singh
MIT Media Lab
Speaker: Yi-Ching(Janet) Huang
Introduction
• ConceptNet
– Freely available commonsense knowledge
base
– Natual-language-processing tool-kit
• It supports many practical textual-
reasoning tasks over real-world
documents
Outline
• Comparison of ConceptNet, Cyc, and
WordNet
• History, Construction and Structure
• Various contextual reasoning tasks
• Quantitative and Qualitative Analysis
• Conclusion
Comparison
Database
content
Resource Capabilities
ConceptNet
(2002)
Commons
ense
OMCS
(from the
public)
(automatic)
Contextual
inference
WordNet
(1985)
Semantic
Lexicon
Expert
(manual)
Lexical
categorisation &
word-similarity
Cyc
(1984)
Commons
ense
Expert
(manual)
Formalized
logical reasoning
History of ConceptNet
Cyc OMCS
CRIS/
OMCSNet ConceptNet
1984 2000 2002 2004
Building ConceptNet
• 3 phases
– Extraction phase
• Extract from OMCS corpus
• English sentence -> binary-relation assertion
– Normalization phase
– Relaxation phase
• Produce “inferred assertion”
• Improve the connectivity of the network
Structure of the ConceptNet
knowledge base
• 1.6 million
assertions (1.25
million are k-lines)
• twenty relation-types
conceptnet_aai conceptualising content.ppt
Practical commonsense
reasoning
• An integrated natural-language-
processing engine
– MontyLingua
– Text document --> VSOO frames
• Reasoning capabilities
– Node-level reasoning
– Document-level reasoning
Node-level reasoning
• Contextual neighborhoods
– Spreading activation
• Analogy-making
• Projection
Document-level reasoning
• Topic-gisting
• Disambiguation and classification
• Novel-concept identification
• Affect sensing
Characteristics and quality
• ConceptNet’s reasoning abilities hinge
largely on the quality of its knowledge
Characteristics of the KB
• The histogram of nodal word-lengths
70%
Characteristic of the KB
• Average frequency an assertion is
uttered of inferred
90% uttered
Characteristics of the KB
• The connectivity of nodes in
ConceptNet by measuring nodal edge-
density
Quality of the knowledge
• Two dimensions of quality of
ConceptNet, rated by human judges
Applications of ConceptNet
ARIA
GOOSE
GloBuddy
MAKEBELIEVE
AAA OMAdventure
Emotus Ponens
Overhear
Bubble Lexicon
LifeNet
SAM
What Would They Think?
Commonsense Predictive Text Entry
Commonsense Investing
Metafor
Commonsense ARIA
• Analyize E-mail’s content and suggest
the related photos
Emotus Ponens
MakeBelieve
Conclusion
• ConceptNet is presently the largest freely
commonsense database
• Support many practical textual-reasoning
tasks
• Goodness
– Easy to use
– Simple structure of WordNet
– Good for practical commonsense reasoning

More Related Content

PDF
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
PPTX
MS-Presentation-new template arid university.pptx
PDF
Integrating Semantic Systems
PPTX
Looking for Commonsense in the Semantic Web
PDF
Ontology learning
PDF
Usage of word sense disambiguation in concept identification in ontology cons...
PPTX
Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...
PPT
Cf intro
NYAI #27: Cognitive Architecture & Natural Language Processing w/ Dr. Catheri...
MS-Presentation-new template arid university.pptx
Integrating Semantic Systems
Looking for Commonsense in the Semantic Web
Ontology learning
Usage of word sense disambiguation in concept identification in ontology cons...
Applied Artificial Intelligence Unit 5 Semester 3 MSc IT Part 2 Mumbai Univer...
Cf intro

Recently uploaded (20)

PDF
Circular Flow of Income by Dr. S. Malini
PPTX
Session 3. Time Value of Money.pptx_finance
PPTX
Session 11-13. Working Capital Management and Cash Budget.pptx
PDF
Chapter 9 IFRS Ed-Ed4_2020 Intermediate Accounting
PDF
Corporate Finance Fundamentals - Course Presentation.pdf
PDF
1a In Search of the Numbers ssrn 1488130 Oct 2009.pdf
PDF
Mathematical Economics 23lec03slides.pdf
PDF
ECONOMICS AND ENTREPRENEURS LESSONSS AND
PDF
how_to_earn_50k_monthly_investment_guide.pdf
PDF
way to join Real illuminati agent 0782561496,0756664682
PPTX
Globalization-of-Religion. Contemporary World
PDF
Spending, Allocation Choices, and Aging THROUGH Retirement. Are all of these ...
PDF
ECONOMICS AND ENTREPRENEURS LESSONSS AND
PPTX
Session 14-16. Capital Structure Theories.pptx
PPTX
The discussion on the Economic in transportation .pptx
PDF
discourse-2025-02-building-a-trillion-dollar-dream.pdf
PPTX
kyc aml guideline a detailed pt onthat.pptx
PDF
NAPF_RESPONSE_TO_THE_PENSIONS_COMMISSION_8 _2_.pdf
PPTX
Introduction to Customs (June 2025) v1.pptx
PDF
illuminati Uganda brotherhood agent in Kampala call 0756664682,0782561496
Circular Flow of Income by Dr. S. Malini
Session 3. Time Value of Money.pptx_finance
Session 11-13. Working Capital Management and Cash Budget.pptx
Chapter 9 IFRS Ed-Ed4_2020 Intermediate Accounting
Corporate Finance Fundamentals - Course Presentation.pdf
1a In Search of the Numbers ssrn 1488130 Oct 2009.pdf
Mathematical Economics 23lec03slides.pdf
ECONOMICS AND ENTREPRENEURS LESSONSS AND
how_to_earn_50k_monthly_investment_guide.pdf
way to join Real illuminati agent 0782561496,0756664682
Globalization-of-Religion. Contemporary World
Spending, Allocation Choices, and Aging THROUGH Retirement. Are all of these ...
ECONOMICS AND ENTREPRENEURS LESSONSS AND
Session 14-16. Capital Structure Theories.pptx
The discussion on the Economic in transportation .pptx
discourse-2025-02-building-a-trillion-dollar-dream.pdf
kyc aml guideline a detailed pt onthat.pptx
NAPF_RESPONSE_TO_THE_PENSIONS_COMMISSION_8 _2_.pdf
Introduction to Customs (June 2025) v1.pptx
illuminati Uganda brotherhood agent in Kampala call 0756664682,0782561496
Ad
Ad

conceptnet_aai conceptualising content.ppt

Editor's Notes

  • #2: There is a lot of information on the Internet today. There are e-mail, instant message and blogs, and so many news online. All of them are text. If there is a tool it can help us to manage and make sense of information, that will be great. ConceptNet is such a tool-kit for a practical commonsens reasoning. And it is free for eveyone.
  • #3: It is my outline today. First of all, I will compare with different databases about ConceptNet, Cyc, and WordNet Secondly, I will present a brief history of ConceptNet, and describe how it was built, and how it is structured. Next, I will introduce several different contextual reasoning tasks that ConceptNet can support. Next, I will show the quantitative and qualitative analysis. Final is a conclusion.
  • #4: ConceptNet : is generated automatically from OMCS corpus (general public) about 4 years WordNet, Cyc: is manually handcrafted by knowledge engineers (knowledge engineers at Cycorp) 20 years ConceptNet : Structure like WordNet, relationally rich like Cyc (simple-to-use representation) (rich content)
  • #5: Motivation: inspired by the success of distributed and collaborative projects on the Web, they turned to volunteers from the general public to massively distribute the problem of building a commonsense knowledge base. OMCS (Open Mind Common Sense) : 30 different activities -> each one elicits a simple assertion CRIS/OMCSNet CRIS (Commonsense Rubost Inferrence System) ConceptNet
  • #6: ConceptNet is built by an automatic process. In first phase, It applies some rules to extract information form OMCS corpus. It maps English sentences to binary-relation assertions. In next phase, it normalizes the extacted nodes. And last is entering in relaxation phase. This phase can improve the connectivity of the semantic network. Consider serveral assertions, it can infer some new assertions. And this new one is called “inferred assertion”.
  • #7: ConceptNet knowledge base consist of 1.6 million assertions and 20 relation-types. K-lines is mean the different sorts of generic conceptual connections. This picture is descrbes the ConecptNet’s relational ontology. (an ontology is a data model that represents a set of concepts within a domain and the relationships between those concepts)
  • #8: Database structure is like this picture and it look likes a mind map. There are 1.6 million edges connecting more than 300 000 nodes. Node are semi-structured English fragments, and edges are relation-types.
  • #9: ConceptNet contains with an intergrated NLP engine, is named MontyLingua. Input a text document, MontyLingua will extract the verb-subject-object-object frames from the document. For example, Mary ate breakfast in this morning. Verb: ate Subject: Mary Object1: breakfast Object2: in this morning And next I will introduce ConceptNet’s two kinds of reasoning capabilities, Node-level and Document-level reasoning.
  • #10: By performing spreading activation, it can radiate outside from the source node and find the contextual neighborhoods. And you can know the relationship between neighborhoods and source nodes. Analogy-making. And projection is like a transitive mechanism form an origin node to another node. It is useful for goal planning and predicting all possible outcomes ant next-states.
  • #11: Given a text-document, ConceptNet can do topic-gisting and know the document’s main ideas. And It can disambiguate the meaning and classify the document to appropriate categories. Except to known concepts, it also can learn the unknown concepts, it so called “Novel-concept identification” Other amazing thing it can do is affect sensing. It can realize the emotion form the document.
  • #13: If we want to know about the complexity of Concept’s nodes. A simple statistic is the histogram of nodal word-lengths. The shorter the nodes, the simple they are likely to be. Look at this graph, approximately 70% of the nodes have a word-length of less than or equal to three. That means the most assertions are simple.
  • #14: 32% are never used.(only inferred) 58% are used only once. And I know that 90% of assertions are used zero times or only one time. It is surprising that there is not more overlap.
  • #15: It is measured by nodal edge-density. The graph is means that k-lines can improve the connectivity of the semantic network.
  • #16: Authors build an experiment with 5 human judges and asked each judge to rate 100 concepts in ConceptNet1.2.
  • #17: There are a lot of interesting applications by using ConceptNet since 2002. Many of them are final term project for a commonsense reasoning course in MIT media Lab during. And Now I will simply introduce 3 applications: ARIA, Emotus Ponens, and MakeBelieve.
  • #18: Commonsense ARIA observes a user writing an e-mail and suggests photos relevant to the user’s story.
  • #19: Emotus Ponens is a textual affect-sensing system. It can analyze the text and classify it to 6 basic emotion categories. (happy, sad, angry, fearful, disgusted, and surprised) EmpathyBuddy is an e-mail client which gives the author automatic affective feedback via emotion face.
  • #20: MakeBelieve is a story-generator that allow a person to interactively invent a story with the system. MAKEBELIEVE will attempt to continue that story by freely imagining possible sequences of events that might happen to the character the user has chosen. The agent uses "commonsense" about causality and how the world works, mined from the Open Mind Common Sense corpus, and combines this with very simple lingustic techniques for story generation to produce pithy but interesting stories. MAKEBELIEVE also uses commonsense to evaluate and critique a story it has written to catch logically inconsistent, incoherent events and actions.
  • #21: ConceptNet is presently the largest freely commonsense databae. it supports many practical textual-reasoning tasks. Its goodness is easy to use, and has the simple structure of WordNet. And it is good for practical commonsense reasoning. It help computer know the semantic meaning from the textual content. Finally, the following speaker will introduce What’s the ConceptNet’s resource, OMCS corpus.?