Home | | Artificial Intelligence | Augmented Transition Networks

Chapter: Artificial Intelligence

Augmented Transition Networks

An augmented transition network, or ATN, is an extended version of a transition network.

Augmented Transition Networks

 

An augmented transition network, or ATN, is an extended version of a transition network.

 

ATNs have the ability to apply tests to arcs, for example, to ensure agreement with number. Thus, an ATN for Sentence would be as shown in Figure 10.2, but the arc from node S2 to S3 would be conditional on the number of the verb being the same as the number for the noun.

Hence, if the noun phrase were three dogs and the verb phrase were is blue, the ATN would not be able to follow the arc from node S2 to S3 because the number of the noun phrase (plural) does not match the number of the verb phrase (singular).

In languages such as French, checks for gender would also be necessary. The conditions on the arcs are calculated by procedures that are attached to the arcs. The procedure attached to an arc is called when the network reaches that arc. These procedures, as well as carrying out checks on agreement, are able to form a parse tree from the sentence that is being analyzed.


Study Material, Lecturing Notes, Assignment, Reference, Wiki description explanation, brief detail
Artificial Intelligence : Augmented Transition Networks |


Privacy Policy, Terms and Conditions, DMCA Policy and Compliant

Copyright © 2018-2024 BrainKart.com; All Rights Reserved. Developed by Therithal info, Chennai.