1 / 29

Dialogue Modeling 2

Dialogue Modeling 2. Indirect Requests. “Can I have a cup of coffee?” One approach to dealing with these kinds of requests is by plan-based inference. Understanding an Indirect Request. Asking if I am able to get a cup of coffee. Interested in my ability to perform the action.

stian
Download Presentation

Dialogue Modeling 2

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Dialogue Modeling 2

  2. Indirect Requests “Can I have a cup of coffee?” • One approach to dealing with these kinds of requests is by plan-based inference

  3. Understanding anIndirect Request Asking if I am able to get a cup of coffee Interested in my ability to perform the action Being able to perform the action is a prerequisite for performing it Must want me to perform that action

  4. Extends to other types of indirect requests too “My soup is cold.” People don’t like cold soup. I have cooked the meal, and Have access to the stove You want me to reheat your soup.

  5. But requires lots of hand coded rules • E.g. : • All of the inferences rules we discussed yesterday • and for the previous example: • People don’t like cold soup • Knowledge that putting soup over an oven will heat it. • Knowing I am able to reheat soup

  6. Instead we can use surface level techniques : Cue-based Inference and Knowledge Poor Methods

  7. Lecture Outline • Lexical cue-based Methods for Interpreting Dialogue Acts • Finite State Methods • Dialogue Managers • HMMs for Interpreting Dialogue Acts • Other Surface Level Dialogue Managers • Frame Based • Agenda Based

  8. Cue-Based Methodsfor Interpretation • Instead of resolving fully, use surface features • “Can you”, “Please” a Request • “Are you”  yes or no question • “Tell me”  Request

  9. Context used also • S : “Would you like to make an appointment with John on Tuesday” • U : “Yes” agreement • S : “Your appointment is with John on Tuesday.” • U : “Yes”  grounding

  10. How would you build these models? • If you had a marked-up training set… • You could collect all of the sentences which you knew to be a particular dialogue act, then you could train a lexical mode : • D = argmax_d P(d | W) = argmax_d P(d) P (d | W)

  11. And Context?  Use a finite-state framework

  12. Lecture Outline • Lexical cue-based Methods for Interpreting Dialogue Acts • Finite State Methods • Dialogue Managers • HMMs for Interpreting Dialogue Acts • Other Surface Level Dialogue Managers • Frame Based • Agenda Based

  13. Finite State Machines a a a b b b Equivalent to regular languages. What is the language accepted by this machine? Is this the minimal machine for this language?

  14. Finite State Dialogue Model What size? large yes medium … small no What toppings? Do you want a pizza? Bye!

  15. Pros • Simple to write • Very robust • Quick • System must direct entire conversation • User actions very limited Cons

  16. Use Variables to shrink Automaton What size? What toppings? Size=response Do you want a pizza?

  17. Lecture Outline • Lexical cue-based Methods for Interpreting Dialogue Acts • Finite State Methods • Dialogue Managers • HMMs for Interpreting Dialogue Acts • Other Surface Level Dialogue Managers • Frame Based • Agenda Based

  18. HMMs • Hidden Markov Models • Probabilistic Finite State Automaton Would you like a bagel? Maybe : .8 Ok Maybe : .2 Are you hungry?

  19. HMMs • So after one turn, don’t necessarily know what state you’re in Would you like a bagel? Maybe : .8 Ok Maybe : .2 Are you hungry?

  20. Dialogue Model opening .23 .76 .63 suggest constrain .19 .99 .77 .18 .36 .18 reject accept .22 .46 closing

  21. What State Are you In? • Combination of what words have been spoken : • P(E|D) : probability of words being spoken given that you’re in state D • And what a reasonable dialogue looks like • P(D) : probability of being in a dialogue state D

  22. This model provides context • By knowing what state you were previously in, makes it easier to determine what the next state will be. • Different lexical frequencies in every state • Different probabilities for each sequences of dialogue states

  23. Lecture Outline • Lexical cue-based Methods for Interpreting Dialogue Acts • Finite State Methods • Dialogue Managers • HMMs for Interpreting Dialogue Acts • Other Surface Level Dialogue Managers • Frame Based • Agenda Based

  24. Frame-Based Dialogue Managers • For appointment scheduler, there are a few distinct things need to be decided • How would you write a finite state machine to get that information? People : ____ Time : _____ Location : _____

  25. This either : • Imposes a very rigid structure • Neglects useful shared structure • Want to flexibly ask for different pieces of the entire bit of information

  26. Frame Driven Model • Solution : have a model where a frame drives the dialogue

  27. Frame-Driven Dialogue User : I’d like to schedule an appointment. System : Who is the other party? User : John Calls up appointment frame People :____ Time : ____ Location : ___ People : John Time : __ Location : ___

  28. Multiple Responses User : I’d like to schedule an appointment. System : Who is the other party? User : John, sometime on tuesday Calls up appointment frame People :____ Time : ____ Location : ___ People : John Time : Tuesday Location : ___

  29. Grounding w/Frames • After each utterance,ground the request User : John, sometime on Tuesday System: Ok where do you want to meet John on Tuesday? • Alternatively can conform when form is finished System : Ok, I am scheduling you in Room 332 with John on Tuesday at 4pm

More Related