Strong Slot-and-Filler Structures

Slides:



Advertisements
Similar presentations
March 1, 2009 Dr. Muhammed Al-Mulhem 1 ICS 482 Natural Language Processing Semantics (Chapter 17) Muhammed Al-Mulhem March 1, 2009.
Advertisements

Natural Language Processing Lecture 2: Semantics.
1 CS 388: Natural Language Processing Story Understanding Raymond J. Mooney University of Texas at Austin.
Conceptual Dependency and Natural Language Processing
KR Using rules IF.. THEN ECA (Event Condition Action) RULES. APLLICATIONS EXAMPLES 1.If flammable liquid was spilled, call the fire department. 2.If the.
Cognitive Linguistics Croft&Cruse
Book Trailer Planning Authors: Book Title:. Job Assignments Storyboard - Media gathering – Music - – Images, graphics - – Video clips - – Text, titles.
Conceptual Dependency ATRANS – abstract transfer (give) PTRANS – physical transfer (move) PROPEL – application of force (push) MTRANS – mental transfer.
Knowledge Representation. Essential to artificial intelligence are methods of representing knowledge. A number of methods have been developed, including:
Knowledge Representation.  What is Knowledge Representation What is Knowledge Representation  Type of knowledge in AI Type of knowledge in AI  Declarative.
CPSC 322 Introduction to Artificial Intelligence November 5, 2004.
Representations One of the major distinctions between ordinary software and AI is the need to represent domain knowledge (or other forms of worldly knowledge)
1 Pertemuan 14 Strong Slot-and-Filler Structures Matakuliah: T0264/Inteligensia Semu Tahun: Juli 2006 Versi: 2/1.
‘People who help us’ Main focus: Prime areas Reception: Term 2 Topic:
Conceptual Dependency
Language, Culture and Communication: Introduction
1 Pertemuan 13 Strong Slot-and-Filler Structures Matakuliah: T0264/Inteligensia Semu Tahun: 2005 Versi: 1/0.
Knowledge Representation
Title: Chinese Characters and Top Ontology in EuroWordNet Paper by: Shun Sylvia Wong & Karel Pala Presentation By: Patrick Baker.
1. Introduction Which rules to describe Form and Function Type versus Token 2 Discourse Grammar Appreciation.
Review Topics Test 1. Background Topics Definitions of Artificial Intelligence & Turing Test Physical symbol system hypothesis vs connectionist approaches.
 Young children view the world very differently from adults.  E.g. no unusual for a child to think the sun follows them.  Field of cognitive psychology.
September 1998HKU Propositional Representation In what language is information “written” in our heads? Is it in the same language we speak? Why is it that.
SEMANTIC ANALYSIS WAES3303
Early Work Masterman: 100 primitive concepts, 15,000 concepts Wilks: Natural Language system using semantic networks Shapiro: Propositional calculus based.
Overview of Verb Tenses UUEG, Chapter 1. The Simple Tenses Simple Present Simple Past Simple Future These tenses make up 90% of the verb tenses we use!
Knowledge Representation. Key Issue in AI 1. Mapping between objects and relations in a problem domain and computational objects and relations in a program.
Albert Gatt LIN3021 Formal Semantics Lecture 4. In this lecture Compositionality in Natural Langauge revisited: The role of types The typed lambda calculus.
Generic Tasks by Ihab M. Amer Graduate Student Computer Science Dept. AUC, Cairo, Egypt.
Cognitive Processes PSY 334 Chapter 5 – Meaning-Based Knowledge Representation.
Knowledge Representation
Levels of Linguistic Analysis
Winter 2007SEG2101 Chapter 31 Chapter 3 Requirements Specifications.
Child Development Theories and Theorists
Knowledge Representation & Game Theory Presented By: Saurabh Sohoney Adil Anis Sandalwala “Once acquired, knowledge must be organized for use” Guided By:
Artificial Intelligence – CS364 Knowledge Representation Lectures on Artificial Intelligence – CS364 Conceptual Dependency 20 th September 2005 Dr Bogdan.
Chapter 9 Knowledge. Some Questions to Consider Why is it difficult to decide if a particular object belongs to a particular category, such as “chair,”
Knowledge Representation. A knowledge base can be organised in several different configurations to facilitate fast inferencing Knowledge Representation.
Chapter 5 – System Modeling
Knowledge Representation Techniques
Chapter 5 System modeling
From Micro-Worlds to Knowledge Representation : AI at an Impasse Hubert L. Dreyfus 15. Oct Presented by BoYun Eom.
Bellwork 9/13/16: 10 minutes to write – I would like at least 8 sentences…
Chapter 5 – System Modeling
Interpretation and Perception
DATA MODELS.
Knowledge Representation & Game Theory
System Modeling Chapter 4
Theme Topic Theme The subject matter discussed in the writing (e.g., geography, love, friendship). Explains what the writing is about. Is generally.
Knowledge Representation
Conceptual Dependency (CD)
Knowledge Representation
Strong Slot-and-Filler Structures
By Dr. lubna Riyadh Abdul Jabber
Preschooler Ch
[Human Memory] 10.Knowledge
KNOWLEDGE REPRESENTATION
Levels of Linguistic Analysis
All Creatures Great and Small.
Ling 566 Oct 14, 2008 How the Grammar Works.
The Outsiders – Chapters 7, 8 & 9 Figurative Language Name:
Semantic Nets and Frames
Structured Knowledge Representation
Subject : Artificial Intelligence
How does your Garden Grow?
Conceptual Dependency Theory
Using Phonemic Awareness &
QUESTION 1B The list of concepts to which questions will relate is as follows: • Genre • Narrative • Representation • Audience • Media language.
Psychology Chapter 8 Section 5: Language.
Knowledge Representation
Presentation transcript:

Strong Slot-and-Filler Structures Chapter 10

Conceptual Dependency Conceptual Dependency (CD) is a theory of how to represent a kind of knowledge about events that is usually contained in natural language sentence. The goal is represent knowledge in a way that: Facilitates drawing references from the sentence. Is independent of the language in which the sentences were originally stated. Capable of read and understand natural language text. Unlike Semantic Nets, which provide only a structure into which nodes representing information at any level can be placed, conceptual dependency provides both a structure and a specific set of primitives, at a particular level of granularity, out of which representations of particular pieces of information can be constructed.

A Simple Conceptual Dependency Representation “I gave the man a book.” where the symbols have the following meanings: Arrows indicate direction of dependency. Double arrow indicates two way link between actor and action. p indicates past tense. ATRANS is one of the primitive acts used by the theory. It indicates transfer of possession. o indicates the object case relation. R indicates the recipient case relation. 236

CD Primitive Actions ATRANS Transfer of an abstract relationship (e.g., give) PTRANS Transfer of the physical location of an object (e.g., go) PROPEL Application of physical force to an object (e.g., push) MOVE Movement of a body part by its owner (e.g., kick) GRASP Grasping of an object by an actor (e.g., clutch) INGEST Ingestion of an object by an animal (e.g., eat) EXPEL Expulsion of something from the body of an animal (e.g., cry) MTRANS Transfer of mental information (e.g., tell) MBUILD Building new information out of old (e.g., decide) SPEAK Production of sounds (e.g., say) ATTEND Focusing of a sense organ toward a. stimulus (e.g., listen) 237

CD Primitive Conceptual Categories ACTs Actions PPs Objects (picture producers) AAs Modifiers of actions (action aiders) PAs Modifiers of PPs (picture aiders) 238

The Dependencies of CD 239

The Dependencies of CD (Cont’d)

CD Conceptual Tenses 240

Using Conceptual Tenses “Since smoking can kill you, I stopped.” 241

The Components of a Script Entry conditions: Conditions that must, in general, be satisfied before the events described in the script can occur. Result Conditions: that will, in general, be true after the events described in the script have occurred. Props: Slots representing objects that are involved in the events described in the script. The presence of these objects can be inferred even if they are not mentioned explicitly. Roles: Slots representing people who are involved in the events described in the script. The presence of these people, too, can be inferred even if they are not mentioned explicitly. If specific individuals are mentioned, they can be inserted into the appropriate slots. Track: The specific variation on a more general pattern that is represented by this particular script. Different tracks of the same script will share many but not all components. Scenes: The actual sequences of events that occur. The events are represented in conceptual dependency formalism. 243

The Restaurant Script 244

Thank you !!!