[go: up one dir, main page]
Scribd
Upload
242 views16 pages

ATN

Augmented transition networks combine different AI technologies like regular transition networks, frames, and conceptual graphs to better handle natural language understanding tasks like subject-verb agreement. The document discusses how augmented transition networks attach procedures to network arcs to check agreement and map parse trees to semantic representations. It also shows how augmented transition networks can be used to build database front-ends that answer English questions with SQL queries.

Uploaded by

xyzking
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
242 views16 pages

ATN

Augmented transition networks combine different AI technologies like regular transition networks, frames, and conceptual graphs to better handle natural language understanding tasks like subject-verb agreement. The document discusses how augmented transition networks attach procedures to network arcs to check agreement and map parse trees to semantic representations. It also shows how augmented transition networks can be used to build database front-ends that answer English questions with SQL queries.

Uploaded by

xyzking
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 16

Augmented Transition Networks:

Combining different AI Technologies for Language Understanding

Motivations

In the last lecture, you have learned to use


regular transition networks to parse a grammar efficiently. This technology has trouble dealing with subject-verb agreement, and other inflectional aspects of the language such as person, tense, and number. Today you will learn about augmented transition networks to handle these difficulties by adding AI technologies previously learned in this course to the basic transition network.

Objectives

1. 2. 3. 4. 5.

Augmented transition networks Dog-world grammar Dog-world knowledge base Information extraction from the Web Database front-end

Regular transition network

A transition network grammar Trace "dog bites"

Invoke parse(verb_phrase) will tell us whether the next section of the input stream is a verb phrase or not. But it does not tell us what kind of verb phrase it is. What person-numbertense? We are going to re-define sentence as a frame and attach procedures to the arcs (transitions) to make augmented transition network.

Augmented transition network ATN parsers Terminals and non-terminals (grammar symbols) are represented as frames. Grammar symbol characteristics are represented as slots:

Dictionary entries for a simple ATN

Parse tree for The dog likes a man

subject-verb agreement

The

dog

likes

man

Attach procedures to arcs

.NOUN_PHRASE

textbook typo p. 609

checking for agreement

Frame data structures

Dog-world knowledge base


Type hierarchy Conceptual graphs for the concept like and the concept bite

Parse tree to semantic representation

1. As usual, to begin, call sentence 2. sentence calls noun_phrase 3. noun_phrase calls noun 4. noun returns concept for dog (1) 5. Article is definite "the dog". Bind a marker #1 to dog (2) 6. sentence calls verb_phrase 7. verb_phrase calls verb which retrieves concept for like (3) 8. verb_phrase calls noun_phrase which calls noun to retrieve man (4) 9. "a man" (5). 10. verb_phrase procedure restricts entity to man and returns (6). 11. sentence procedure joins dog: #1 to experiencer (7).

SQL Database query

English: SQL:

What is John Smith's salary? select salary from employee_salary where employee ="John Smith"

Database query 2

List the salaries of employees who work for Ed Angel. select salary from employee_salary, manager_of_hire where manager = "Ed Angel" and manager_of_hire.employee = employee_salary.employee

Entity-relationship diagrams

Combine entity-relationship diagram with conceptual graph


Database entity-relationship diagram

Who hired this employee?


AI knowledge base conceptual graph

Who hired john smith?

Conclusion

Natural language understanding is one of the


most difficult problems in AI, even though little kids seem to learn languages effortlessly. You have seen how the following AI technologies have been used to process natural language: FOL, grammars, parsing, semantic networks, transition networks, frames, augmented transition networks, and conceptual graphs. These AI techniques have been successful applied to database front-ends and expert system interfaces.

You might also like