DOC PREVIEW
UT CS 378 - Discourse

This preview shows page 1-2-3-4 out of 13 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 13 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 13 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 13 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 13 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 13 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

DiscourseMore than One Sentence at a TimeOr Dialogue ManagementOr Machine TranslationReference ResolutionPronounsOne AnaphoraA Discourse ModelA Blackboard ModelConstraint SourcesThe ProcessKinds of Constraint SourcesCoherenceDiscourseRead J & M Chapter 18.1More than One Sentence at a TimeThe alphas have a long-standing hatred of the betas. Their leaders have decided that the time has come to launch an attack. They are considering the Thanksgiving weekend.Suppose we are trying to do text extraction and we want to fill in records such as:attack (status <planned, imminent, active, completed>)(attacker )(attackee )(location )(mode-of-attack )(time-of-attack )(credit-claimer )Or Dialogue ManagementReference resolution:> Who planned the October attack? The UMPA guerrillas.> Who is their leader?Coherence: http://www.alicebot.org/Or Machine TranslationEnglish: John saw a new bicycle at the store. He wants it.French: John a vu une nouvelle bicyclette au magasin. Il le/la veut.from Babel Fish: John a vu une nouvelle bicyclette au magasin. Il le veut.Reference ResolutionIndefinite NPs: A boy and a girl came in. They were happy. The girl laughed.Definite NPs: The city council will vote tomorrow. John went to the store/hospital. (brit) John went to hospital.Pronouns1. John went wrote a new book. It is a bestseller. 2. John went to the store with Bill. He bought a new TV.3. John was the first person to get there. Bill arrived a bit later. He brought the cookies and tea.4. John parked his car in his garage. It is incredibly messy, with old bike and car parts lying around everywhere.5. John parked his car in Beverly Hills. It is incredibly messy, with old bike and car parts lying around everywhere.6. Nancy ate her oatmeal this morning because she heard that it lowers cholesterol. 7. Nancy hates raccoons because they ate her corn last year.8. If a farmer owns a donkey, he beats it.9. If a farmer doesn’t own a donkey, he beats it.10. Why don’t they ever fix the roads?One Anaphora1. I just saw the new Hondas. I want one.2. Reserve a seat for me on the flight. Reserve one for Jack too. 3. John has a red jumper and a blue one.4. I saw two bears in the woods. Bill saw some in the parking lot too.5. Is there a flight to Melbourne before 7am? No but there is one at 9.A Discourse ModelA realistic model has three layers:•Linguistic•Discourse (pegs)•Knowledge baseExamples:There are a lot of books in the room. Pick one. Look at the title page. It should contain both the author’s name and the title. John wants Bill to know about the movie. He thinks he would like it.A Blackboard ModelConstraint SourcesEach constraint source has four components:•Modeller•Constraint poster•Proposer•EvaluatorThe ProcessEach CS updates its model if necessary.Each CS posts constraints if necessary. Example: He saw him.Each CS has the opportunity to propose candidates.Evaluation:niniiconfidenceiconfidenceiscorererunningsco11)()()(Kinds of Constraint SourcesFinite set generators (e.g., reflexive pronouns)Fading infinite set generators (e.g., recency)Filters (number agreement)Preferences (semantic coherence)CoherenceMary gave Sue her favorite book. It was hard to part with it, but she knew it would be appreciated.Mary gave Sue her favorite book. She’ll always be grateful for that.Mary gave Sue her favorite book. She’s very tall. The problem with coherence: It appears to be an AI complete


View Full Document

UT CS 378 - Discourse

Documents in this Course
Epidemics

Epidemics

31 pages

Phishing

Phishing

49 pages

Load more
Download Discourse
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Discourse and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Discourse 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?