Download presentation
Presentation is loading. Please wait.
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
05-22-2002RavenClaw: a new DM architecture2 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.
3
05-22-2002RavenClaw: a new DM architecture3 A View from far, far away What did you just say ? Try opening that hatch SELECT * WHERE … Since that failed, I need you to push button B Can you repeat that, please ? Suspend… Resume … Conversational Skills Dialog Task Specification Backend Core 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
4
05-22-2002RavenClaw: a new DM architecture4 Outline Goals A view from far away Main ideas Dialog Task Specification / Execution Conversational skills In more detail Dialog Task Specification / Execution Conversational skills Conversational DTS Backend Core
5
05-22-2002RavenClaw: a new DM architecture5 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 DTS Communicator Welcome LoginTravelLocals Bye AskRegistered AskName GreetUserGetProfile Leg1 DepartLocationArriveLocation
6
05-22-2002RavenClaw: a new DM architecture6 Handling inputs Communicator Welcome LoginTravelLocals Bye AskRegistered AskName GreetUserGetProfile Leg1 DepartLocationArriveLocation 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 DTS
7
05-22-2002RavenClaw: a new DM architecture7 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. Conversational
8
05-22-2002RavenClaw: a new DM architecture8 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 Conversational
9
05-22-2002RavenClaw: a new DM architecture9 Outline Goals A view from far away Main ideas Dialog Task Specification / Execution Conversational skills In more detail Dialog Task Specification / Execution Conversational skills DTS
10
05-22-2002RavenClaw: a new DM architecture10 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 … ?
11
05-22-2002RavenClaw: a new DM architecture11 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…
12
05-22-2002RavenClaw: a new DM architecture12 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.
13
05-22-2002RavenClaw: a new DM architecture13 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.
14
05-22-2002RavenClaw: a new DM architecture14 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
15
05-22-2002RavenClaw: a new DM architecture15 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
16
05-22-2002RavenClaw: a new DM architecture16 [Name] [Registered] [Hotel] [Bye] Input Pass 1. Construct an agenda of expectations (Partially?) ordered list of concepts expected by the system [ArrivalCity][DepartureCity] Co Welcome LoginTravelLocals Bye Regist. Nam GreetProf. Leg1 DepArr Focused
17
05-22-2002RavenClaw: a new DM architecture17 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 [Name] [Registered] [Hotel] [Bye] [ArrivalCity] [DepartureCity] I’m flying to San Francisco and I need a hotel there.
18
05-22-2002RavenClaw: a new DM architecture18 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)
19
05-22-2002RavenClaw: a new DM architecture19 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)
20
05-22-2002RavenClaw: a new DM architecture20 Outline Goals A view from far away Main ideas Dialog Task Specification / Execution Conversational skills In more detail Dialog Task Specification / Execution Conversational skills Conversational Core
21
05-22-2002RavenClaw: a new DM architecture21 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
22
05-22-2002RavenClaw: a new DM architecture22 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 ?
23
05-22-2002RavenClaw: a new DM architecture23 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
24
05-22-2002RavenClaw: a new DM architecture24 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
25
05-22-2002RavenClaw: a new DM architecture25 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
26
05-22-2002RavenClaw: a new DM architecture26 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 …
27
05-22-2002RavenClaw: a new DM architecture27 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 ?
28
05-22-2002RavenClaw: a new DM architecture28 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 ?
29
05-22-2002RavenClaw: a new DM architecture29 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 ?
30
05-22-2002RavenClaw: a new DM architecture30 Mechanisms DepartureCity = 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 ?
31
05-22-2002RavenClaw: a new DM architecture31 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
32
05-22-2002RavenClaw: a new DM architecture32 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 !
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.