1 / 43

Adding Common Sense into Artificial Intelligence

Adding Common Sense into Artificial Intelligence. Common Sense Computing Initiative Software Agents Group MIT Media Lab. Why do computers need common sense?. Conversation works because of unspoken assumptions People tend not to provide information they consider extraneous (Grice, 1975)

lynette
Download Presentation

Adding Common Sense into Artificial Intelligence

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Adding Common Sense intoArtificial Intelligence Common Sense Computing Initiative Software Agents Group MIT Media Lab

  2. Why do computers need common sense? • Conversation works because of unspoken assumptions • People tend not to provide information they consider extraneous (Grice, 1975) • Understanding language requires understanding connections

  3. What can computers do with common sense? Understand the context of what the user wants Fill in missing information using background knowledge Discover trends in what people mean, not just what they say But how do we collect it?

  4. A Brief Outline • What is OMCS? • What is ConceptNet? • Using AnalogySpace for Inference • Using Blending for Intuition • OMCS Applications

  5. Open Mind Common Sense Project • Collecting common sense from internet volunteers since 2000 • We have over 1,000,000 pieces of English language knowledge from 15,000 contributors • Multilingual • Additional resources in Chinese, Portuguese, Korean, Japanese, and Dutch • In-progress: Spanish and Hungarian • Users consider 87% of statements used in ConceptNet to be true

  6. “A coat is used for keeping warm.” “People want to be respected.” “The sun is very hot.” “The last thing you do when you cook dinner is wash your dishes.” “People want good coffee.” What kind of knowledge?

  7. Where does the knowledge come from? • Contributors on our Web site (openmind.media.mit.edu) • Games that collect knowledge

  8. What is ConceptNet? • A semantic network representation of the OMCS database (Liu and Singh, 2004) • Over the years, used for: affect sensing, photo and video storytelling, text prediction, goal-oriented interfaces, speech recognition, task prediction, … • ConceptNet 4.0 • Over 300,000 connections between ~80,000 concepts • Natural language processing tools to help line up your data with ConceptNet

  9. An Example

  10. Creation of ConceptNet • A shallow parser turns natural language sentences into ConceptNet assertions • 59 top-level patterns for English, such as “You would use {NP} to {VP}” • {NP} and {VP} candidates identified by a chart parser

  11. Representation • Statement: expresses a fact in natural language • Assertion: asserts that a relation exists between two concepts • Concepts: sets of related phrases • identified by lemmatizing (or stemming) and removing stop words • Relations: one of 25: • IsA, UsedFor, HasA, CapableOf, Desires, CreatedBy, AtLocation, CausesDesire, …

  12. Example

  13. Reliability • Reliability increases when more users affirm that a statement is true • by entering equivalent statements independently • by rating existing statements on the Web • Each assertion gets a weight according to how many users support it

  14. Polarity • Allows predicates that express true, negative information: “Pigs cannot fly” • Negated assertions are represented by negative weights • Reliability and polarity are independent

  15. AnalogySpace • Technique for learning, reasoning, and analyzing using common sense • AnalogySpace can: • generalize from sparsely-collected knowledge • confirm or question existing knowledge • classify information in a knowledge base in a variety of ways • Can use the same technique in other domains: businesses, people, communities, opinions

  16. AnalogySpace Overview • Finds patterns in knowledge • Builds a representation in terms of those patterns • Finds additional knowledge using the combination of those patterns • Uses dimensionality reduction via Singular Value Decomposition

  17. Input to the SVD • Input to SVD: matrix of concepts vs. features • Feature: a concept, a relation, and an open slot, e.g., (. . . , MadeOf, metal) • Concepts × features = assertions

  18. The Input Matrix • For consistency, we scale each concept to unit Euclidean magnitude

  19. Running the SVD

  20. The Truncated SVD Truncating the SVD smoothes over sparse data.

  21. Good vs. Bad

  22. Reasoning with AnalogySpace • Similarity represented by dot products of concepts (AAT) • Approximately the cosine of their angle

  23. Reasoning with AnalogySpace • Predictions represented by dot products of concepts with features

  24. Contributors are in the loop

  25. Ad-hoc Categories

  26. What can we use common sense for? • A “sanity check” on natural language • Text prediction • Affect sensing • Recommender systems • “Knowledge management”

  27. Common Sense in Context • We don’t just use common sense to make more common sense • Helps a system make sense of everyday life • Making connections in domain-specific information • Understanding free text • Bridging different knowledge sources

  28. Digital Intuition • Add common sense intuition • Using similar techniques to make connections and inference between data sets • Create a shared “Analogy”Space from two data sets using Blending

  29. Blending • Two data sets are combined in a way to maximize the interaction between the data sets • They are weighted by a factor: C = (1 – f)A + fB

  30. Blending Creates aNew Representation • With f = 0 or 1, equivalent to projecting one dataset into the other’s space • In the middle, representation determined by both datasets.

  31. No overlap = no interaction A’s singular values B’s singular values

  32. Overlap -> Nonlinear Interaction (Veering)

  33. Overlap -> Nonlinear Interaction

  34. SVD over Multiple Data Sets • Convert all data sets to matrices • Find a rough alignment between the matrices • Some rows or features • Find a blending factor • Maximize veering or interaction • Run the AnalogySpace process jointly

  35. Blends of Multiple Data Sets • You can blend more than two things • Simple blending heuristic: scale all your data so that their largest singular vectors are equal

  36. Applications • Inference over domain specific data • Word sense disambiguation • Data visualization and analysis • Finance

  37. Tools we Distribute • The OMCS database • ConceptNet • Divisi • In development: the Luminoso visualizer

  38. The Common Sense Computing Initiative Web: http://csc.media.mit.edu/ Email: conceptnet@media.mit.edu Thank you!

More Related