1 / 32

RavenClaw

RavenClaw . An improved dialog management architecture for task-oriented spoken dialog systems Presented by: Dan Bohus (dbohus@cs.cmu.edu) Work by: Dan Bohus, Alex Rudnicky, Andrew Hoskins Carnegie Mellon University, 2002. New DM Architecture: Goals.

johana
Download Presentation

RavenClaw

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. RavenClaw An improved dialog management architecture for task-oriented spoken dialog systems Presented by: Dan Bohus (dbohus@cs.cmu.edu) Work by: Dan Bohus, Alex Rudnicky, Andrew Hoskins Carnegie Mellon University, 2002

  2. New DM Architecture: Goals • Able to handle complex, goal-directed dialogs • Go beyond (information access systems and) the slot-filling paradigm • Easy to develop and maintain systems • Developer focuses only on dialog task • Automatically ensure a minimum set of task-independent, conversational skills • Open to learning (hopefully both at task and discourse levels) • Open to dynamic SDS generation • More careful, more structured code, logs, etc: provide a robust basis for future research. RavenClaw: a new DM architecture

  3. Backend Dialog Task Specification Conversational Skills Core A View from far, far away • Let the developer focus only on the dialog task spec.: • Don’t worry about misunderstandings, the accuracy of concepts, repeats, focus shifts, barge-ins, etc… merely describe (program) the task, assuming perfect knowledge of the world • Automatically generate the conversational mechanisms SELECT * WHERE … Try opening that hatch Since that failed, I need you to push button B Can you repeat that, please ? Suspend… Resume … What did you just say ? RavenClaw: a new DM architecture

  4. Backend DTS Conversational Core Outline • Goals • A view from far away • Main ideas • Dialog Task Specification / Execution • Conversational skills • In more detail • Dialog Task Specification / Execution • Conversational skills RavenClaw: a new DM architecture

  5. Communicator Welcome Login Travel Locals Bye AskRegistered GreetUser GetProfile Leg1 AskName DTS DepartLocation ArriveLocation Dialog Task Spec & Execution • Dialog Task implemented by a hierarchy of agents • Handle and Operate based on concepts • Execution with interleaved Input Passes. • Execute the agents by top-down “planning” • Do input passes when information is required • REMEMBER: This is just the dialog task RavenClaw: a new DM architecture

  6. Communicator Welcome Login Travel Locals Bye AskRegistered GreetUser GetProfile Leg1 AskName DTS DepartLocation ArriveLocation Handling inputs • Input Pass • Assemble an agenda of expectations (open concepts) • Bind values from the input to the concepts • Process non-understanding (if), analyze need for focus shifts • Continue execution RavenClaw: a new DM architecture

  7. Conversational Conversational Skills /Mechanisms • A lot of problems in SDS generated by lack of conversational skills. “It’s all in the little details!” • Dealing with misunderstandings • Generic channel/dialog mechanisms : repeats, focus shift, context establishment, help, start over, etc, etc. • Timing • Even when these mechanisms are in, they lack uniformity & consistency. • Development and maintenance are time consuming. RavenClaw: a new DM architecture

  8. Conversational Conversational Skills / Mechanisms • The core takes care of these by dynamically inserting appropriate agencies in the task tree • A list of (more or less) task independent mechanisms: • Implicit/Explicit Confirmations, Clarifications, Disambiguation = the whole Misunderstandings problem • Context reestablishment • Timeout and Barge-in control • Back-channel absorption • Generic dialog mechanisms: • Repeat, Suspend… Resume, Help, Start over, Summarize, Undo, Querying the system’s belief RavenClaw: a new DM architecture

  9. DTS Outline • Goals • A view from far away • Main ideas • Dialog Task Specification / Execution • Conversational skills • In more detail • Dialog Task Specification / Execution • Conversational skills RavenClaw: a new DM architecture

  10. Dialog Task Specification • Goal: able to handle complex domains, beyond information access, frame-based, slot-filling systems i.e. : • Symphony, Intelligent checklists, Navigation, Route planning • We need a powerful enough formalism to describe all these tasks: • C++ code ? • Declarative would be nice … but is it powerful enough ? • Templatized C++ code … ? RavenClaw: a new DM architecture

  11. Dialog Task Specification • Tree of predefined agents types: • Inform, Request, Expect, Execute • Each agent has: • A set of concepts • Preconditions • Success Criteria • Effects • Focus Criteria (triggers) • Concepts • Data, Type (basic, struct, array) • Confidence/Value, Availability, Ambiguousness, Groundedness, System/User, TurnAcquired, TurnConveyed, etc… RavenClaw: a new DM architecture

  12. An example DTS UserLogin: AGENCY concepts: registered(BOOL), name(STRING), id(STRING), profile(PROFILE), profile_found(BOOL) achieves_when: profile || InformProfileNotFound AskRegistered: REQUEST(registered) grammar: {[yes]->true,[no]->false,[guest]->false} AskName: REQUEST(name) precond: registered==no grammar: [user_name] max_attemps: 2 InformGreetUser: INFORM precond: name AskID: REQUEST(id) precond: registered==yes mapping: [user_id] DoProfileRetrieval: EXECUTE precond: name || id call: ABEProfile.Call >name, >id, <profile, <profile_found InformProfileNotFound: INFORM precond: !profile_found Given that the baseline is 259 lines of C++ code, this is pretty good. RavenClaw: a new DM architecture

  13. Can a formalism cut it ? • People have repeatedly tried formalizing dialog … and failed  • We’re focusing only on the task (like in robotics/execution) • Actually, these agents are all C++ classes, so we can backoff to code; the hope is that most of the behaviors can be easily expressed as above. RavenClaw: a new DM architecture

  14. DTS execution • Agency.Execute() decides which subagent is executed next, based on preconditions • Various simple policies can be implemented • Left-to-right (open/closed), choice, etc • But free to do more sophisticated things (MDPs, etc) ~ learning at the task level RavenClaw: a new DM architecture

  15. Libraries of DTS agencies ? • Provide a library of “common task” and “common discourse” agencies • Frame agency • List browse agency • Choose agency • Disambiguate agency, Ground Agency, … • Etc RavenClaw: a new DM architecture

  16. Co Welcome Login Travel Locals Bye Regist. Greet Prof. Leg1 Nam [DepartureCity] [ArrivalCity] Dep Arr [Name][Registered][Hotel][Bye] Input Pass 1. Construct an agenda of expectations • (Partially?) ordered list of concepts expected by the system Focused RavenClaw: a new DM architecture

  17. [DepartureCity] [ArrivalCity] [Name][Registered][Hotel][Bye] Input Pass (continued) 2. Bind values/confidences to concepts • The System <> Mixed Initiative spectrum can be expressed in terms of the way the agenda is constructed and binding policies, independent of task I’m flying to San Francisco andI need a hotel there. RavenClaw: a new DM architecture

  18. Input pass (continued) 3. Process non-understandings (iff) - try and detect source and inform user: • Channel (SNR, clipping) • Decoding (confidence score, prosody) • Parsing (parsing scores) • Dialog level (parse ok, but no expectation match) RavenClaw: a new DM architecture

  19. Input Pass 4. Focus shifts • Focus shifts seem to be task dependent. Decision to shift focus is taken by the task (DTS) • But they also have a TI-side (sub-dialog size, context reestablishment). Context reestablishment is handled automatically, in the Core (see later) RavenClaw: a new DM architecture

  20. Conversational Core Outline • Goals • A view from far away • Main ideas • Dialog Task Specification / Execution • Conversational skills • In more detail • Dialog Task Specification / Execution • Conversational skills RavenClaw: a new DM architecture

  21. Task-Independent, Conversational Mechanisms • Should be transparently handled by the core • However, the developer should be able to write his own customized mechanisms if needed • Most cases handled by inserting extra “discourse” agents on the fly in the dialog task tree RavenClaw: a new DM architecture

  22. Conversational Skills: A List • The grounding / misunderstandings problems • Universal dialog mechanisms: • Repeat, Suspend… Resume, Help, Start over, Summarize, Undo, Querying the system’s belief • Timing and Barge-in control • Focus Shifts, Context Establishment • Back-channel absorption • Q: To which extent can we abstract these away from the Dialog Task ? RavenClaw: a new DM architecture

  23. UDM: Repeat • Repeat (simple) • The DTT is adorned with a “Repeat” Agency automatically at start-up • Which calls upon the OutputManager • Not all outputs are “repeatable” (i.e. implicit confirms, gui, )… which ones exactly… ? • Repeat (with referents) • only 3%, they are mostly [summarize] • User-defined custom repeat agency RavenClaw: a new DM architecture

  24. UDM: Help • DTT adorned at start-up with a help agency • Can capture and issue: • Local help (obtained from focused agent) • ExplainMore help (obtained from focused) • What can I say ? • Contextual help (obtained from main topic) • Generic help (give_me_tips) • Obtains Help prompts from the focused agent and the main topic (defaults provided) • Default help agency can be overwritten by user RavenClaw: a new DM architecture

  25. UDM: Suspend … Resume • DTT adorned with a SuspendResume agency. • Context reestablishment • Automatically when focusing back after a sub-dialog • Construct a model for that (given size of sub-dialog, time issues, etc) • Prompts problem shifted to the NLG RavenClaw: a new DM architecture

  26. UDM: Start over, Summarize • Start over: • DTT adorned with a Start-Over agency • Summarize: • DTT adorned with a Summarize agency • prompt generated automatically • problem shifted to NLG … RavenClaw: a new DM architecture

  27. Timing & barge-in control • Knowledge of barge-in location • Information on what got conveyed is fed back to the DM • Special agencies can take special action based on that (I.e. List Browsing) • Can we determine what are non-barge-in-able utterances in a task-independent manner ? RavenClaw: a new DM architecture

  28. Confirmation, Clarif., Disamb., Misunderstandings, Grounding… • Largely unsolved: this is next ! • 2 components: • Confidence scores/computation on concepts • Obtaining them • Updating them • Taking the “right” decision based on those scores: • Insert appropriate agencies on the fly in the dialog task tree: opportunity for learning • What’s the set of decisions / agencies ? • How do you decide ? RavenClaw: a new DM architecture

  29. Confidence scores • Obtaining conf. Scores: from annotator • Updating them, from different sources: • (Un)Attacked implicit/explicit confirms • Correction detector • Elapsed time ? • Domain knowledge • Priors ? • But how do you integrate all these in a principled way ? RavenClaw: a new DM architecture

  30. Mechanisms • DepartureCity = <Seattle,0.71><SF,0.29> • Implicit / Explicit confirmations • When do you leave from Seattle ? • So you’re leaving from Seattle… When ? • Clarifications • Did you say you were leaving from Seattle ? • Disambiguation • I’m sorry was that Seattle or San Francisco? • How do you decide which ? • Learning ? RavenClaw: a new DM architecture

  31. Software Engineering • Provide a robust basis for future research. • Modularity • Separability between task and discourse • Separability of concepts and confidence computations • Portability • Mutiple servers • Aggressive, structured, timed logging RavenClaw: a new DM architecture

  32. Conclusion • New DM framework • separation of dialog task from conversational mechanisms • developer can focus only on dialog task • conversational mechanisms generated automatically • easier development/maintenance • robust platform for future research • Most of the implementation completed • Symphony/LARRI reimplemented • Next: back to misunderstandings ! RavenClaw: a new DM architecture

More Related