Conceptual Dependency in Artificial Intelligence

Conceptual Dependency:

In 1977, Roger C. Schank has developed a Conceptual Dependency structure. The Conceptual Dependency is used to represent knowledge of Artificial Intelligence. It should be powerful enough to represent these concepts in the sentence of natural language. It states that different sentence which has the same meaning should have some unique representation. There are 5 types of states in Conceptual Dependency:

    1. Entities
    2. Actions
    3. Conceptual cases
    4. Conceptual dependencies
    5. Conceptual tense

Main Goals of Conceptual Dependency:

1. It captures the implicit concept of a sentence and makes it explicit.
2. It helps in drawing inferences from sentences.
3. For any two or more sentences that are identical in meaning. It should be only one representation of meaning.
4. It provides a means of representation which are language independent.
5. It develops language conversion packages.

Rules of Conceptual Dependency:

Rule-1: It describes the relationship between an actor and the event he or she causes.

Rule-2: It describes the relationship between PP and PA that are asserted to describe it.

Rule-3: It describes the relationship between two PPs, one of which belongs to the set defined by the other.

Rule-4: It describes the relationship between a PP and an attribute that has already been predicated on it.

Rule-5: It describes the relationship between two PPs one of which provides a particular kind of information about the other.

Rule-6: It describes the relationship between an ACT and the PP that is the object of that ACT.

Rule-7: It describes the relationship between an ACT and the source and the recipient of the ACT.

Rule-8: It describes the relationship between an ACT and the instrument with which it is performed. This instrument must always be a full conceptualization, not just a single physical object.

Rule-9: It describes the relationship between an ACT and its physical source and destination.

Rule-10: It represents the relationship between a PP and a state in which it started and another in which it ended.

Rule-11: It represents the relationship between one conceptualization and another that causes it.

Rule-12: It represents the relationship between conceptualization and the time at which the event occurred described.

Rule-13: It describes the relationship between one conceptualization and another, that is the time of the first.

Rule-14: It describes the relationship between conceptualization and the place at which it occurred.

Advantages of Conceptual Dependency:

1. Decomposed words into primitives so that language processing focuses on general concepts instead of individual words.

2. Canonical representation captures commonality across different words and structures.

3. Inter-lingual representation facilitates machine translation.

4. Words trigger CD frames that provide predictions about what will come next. Identifies conceptual roles and helps disambiguation.

5. We can infer properties of unknown words. Inferences are attached to general concepts so inference rules are not overwhelming.

Disadvantages of Conceptual Dependency:

1. Incompleteness

2. Primitives

3. No higher level concepts

4. Many inferences not organized around primitives.