spoken dialogue systems n.
Skip this Video
Loading SlideShow in 5 Seconds..
Spoken Dialogue Systems PowerPoint Presentation
Download Presentation
Spoken Dialogue Systems

Loading in 2 Seconds...

play fullscreen
1 / 136

Spoken Dialogue Systems - PowerPoint PPT Presentation

  • Uploaded on

Spoken Dialogue Systems. Julia Hirschberg CS 4706. Today. Basic Conversational Agents ASR NLU Generation Dialogue Manager Dialogue Manager Design Finite State Frame-based Initiative: User, System, Mixed Information-State Dialogue-Act Detection Dialogue-Act Generation Evaluation

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Spoken Dialogue Systems' - torie

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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
spoken dialogue systems

Spoken Dialogue Systems

Julia Hirschberg

CS 4706

  • Basic Conversational Agents
    • ASR
    • NLU
    • Generation
    • Dialogue Manager
  • Dialogue Manager Design
    • Finite State
    • Frame-based
    • Initiative: User, System, Mixed
  • Information-State
    • Dialogue-Act Detection
    • Dialogue-Act Generation
    • Evaluation
    • Utility-based conversational agents
      • MDP, POMDP
conversational agents
Conversational Agents
  • AKA:
    • Interactive Voice Response Systems
    • Dialogue Systems
    • Spoken Dialogue Systems
  • Applications:
    • Travel arrangements (Amtrak, United airlines)
    • Telephone call routing
    • Tutoring
    • Communicating with robots
    • Anything with limited screen/keyboard
conversational structure
Conversational Structure
  • Telephone conversations
    • Stage 1: Enter a conversation
    • Stage 2: Identification
    • Stage 3: Establish joint willingness to converse
    • Stage 4: First topic is raised, usually by caller
why is this customer confused
Why is this customer confused?
  • Customer: (rings)
  • Operator: Directory Enquiries, for which town please?
  • Customer: Could you give me the phone number of um: Mrs. um: Smithson?
  • Operator: Yes, which town is this at please?
  • Customer: Huddleston.
  • Operator: Yes. And the name again?
  • Customer: Mrs. Smithson
why is this customer confused1
Why is this customer confused?
  • A: And, what day in May did you want to travel?
  • C: OK, uh, I need to be there for a meeting that’s from the 12th to the 15th.
  • Note that client did not answer question.
  • Meaning of client’s sentence:
    • Meeting
      • Start-of-meeting: 12th
      • End-of-meeting: 15th
    • Doesn’t say anything about flying!!!!!
  • How does agent infer client is informing him/her of travel dates?
will this client be confused
Will this client be confused?

A: … there’s 3 non-stops today.

  • True if in fact 7 non-stops today.
  • But agent means: 3 and only 3.
  • How can client infer that agent means:
    • only 3
grice conversational implicature
Grice: conversational implicature
  • Implicature means a particular class of licensed inferences.
  • Grice (1975) proposed that what enables hearers to draw correct inferences is:
  • Cooperative Principle
    • This is a tacit agreement by speakers and listeners to cooperate in communication
4 gricean maxims
4 Gricean Maxims
  • Relevance: Be relevant
  • Quantity: Do not make your contribution more or less informative than required
  • Quality: try to make your contribution one that is true (don’t say things that are false or for which you lack adequate evidence)
  • Manner: Avoid ambiguity and obscurity; be brief and orderly
  • A: Is Regina here?
  • B: Her car is outside.
  • Implication: yes
    • Hearer thinks: why would he mention the car? It must be relevant. How could it be relevant? It could since if her car is here she is probably here.
  • Client: I need to be there for a meeting that’s from the 12th to the 15th
    • Hearer thinks: Speaker is following maxims, would only have mentioned meeting if it was relevant. How could meeting be relevant? If client meant me to understand that he had to depart in time for the mtg.
  • A:How much money do you have on you?
  • B: I have 5 dollars
    • Implication: not 6 dollars
  • Similarly, 3 non stops can’t mean 7 non-stops (hearer thinks:
    • if speaker meant 7 non-stops she would have said 7 non-stops
  • A: Did you do the reading for today’s class?
  • B: I intended to
    • Implication: No
    • B’s answer would be true if B intended to do the reading AND did the reading, but would then violate maxim
speech recognition
Speech recognition
  • Input: acoustic waveform
  • Output: string of words
    • Basic components:
      • a recognizer for phones, small sound units like [k] or [ae].
      • a pronunciation dictionary like cat = [k ae t]
      • a grammar telling us what words are likely to follow what words
      • A search algorithm to find the best string of words
natural language understanding
Natural Language Understanding
  • Or “NLU”
  • Or “Computational semantics”
  • There are many ways to represent the meaning of sentences
  • For speech dialogue systems, most common is “Frame and slot semantics”.
an example of a frame
An example of a frame
  • Show me morning flights from Boston to SF on Tuesday.




CITY: Boston

DATE: Tuesday

TIME: morning


CITY: San Francisco

how to generate this semantics
How to generate this semantics?
  • Many methods,
  • Simplest: “semantic grammars”
  • We’ll come back to these after we’ve seen parsing.
  • But a quick teaser for those of you who might have already seen parsing:
  • CFG in which the LHS of rules is a semantic category:
    • LIST -> show me | I want | can I see|…
    • DEPARTTIME -> (after|around|before) HOUR | morning | afternoon | evening
    • HOUR -> one|two|three…|twelve (am|pm)
    • FLIGHTS -> (a) flight|flights
    • ORIGIN -> from CITY
    • CITY -> Boston | San Francisco | Denver | Washington
semantics for a sentence
Semantics for a sentence


Show me flights from Boston


to San Francisco on Tuesday



generation and tts
Generation and TTS
  • Generation component
    • Chooses concepts to express to user
    • Plans out how to express these concepts in words
    • Assigns any necessary prosody to the words
  • TTS component
    • Takes words and prosodic annotations
    • Synthesizes a waveform
generation component
Generation Component
  • Content Planner
    • Decides what content to express to user
      • (ask a question, present an answer, etc)
    • Often merged with dialogue manager
  • Language Generation
    • Chooses syntactic structures and words to express meaning.
    • Simplest method
      • All words in sentence are prespecified!
      • “Template-based generation”
      • Can have variables:
        • What time do you want to leave CITY-ORIG?
        • Will you return to CITY-ORIG from CITY-DEST?
more sophisticated language generation component
More sophisticated language generation component
  • Natural Language Generation
  • Approach:
    • Dialogue manager builds representation of meaning of utterance to be expressed
    • Passes this to a “generator”
    • Generators have three components
      • Sentence planner
      • Surface realizer
      • Prosody assigner
hci constraints on generation for dialogue coherence
HCI constraints on generation for dialogue: “Coherence”
  • Discourse markers and pronouns (“Coherence”):

(1) Please say the date.

Please say the start time.

Please say the duration…

Please say the subject…

(2) First, tell me the date.

Next, I’ll need the time it starts.

Thanks. <pause> Now, how long is it supposed to last?

Last of all, I just need a brief description



hci constraints on generation for dialogue coherence ii tapered prompts
HCI constraints on generation for dialogue: coherence (II): tapered prompts
  • Prompts which get incrementally shorter:
  • System: Now, what’s the first company to add to your watch list?
  • Caller: Cisco
  • System: What’s the next company name? (Or, you can say, “Finished”)
  • Caller: IBM
  • System: Tell me the next company name, or say, “Finished.”
  • Caller: Intel
  • System: Next one?
  • Caller: America Online.
  • System: Next?
  • Caller: …
dialogue manager
Dialogue Manager
  • Controls the architecture and structure of dialogue
    • Takes input from ASR/NLU components
    • Maintains some sort of state
    • Interfaces with Task Manager
    • Passes output to NLG/TTS modules
four architectures for dialogue management
Four architectures for dialogue management
  • Finite State
  • Frame-based
  • Information State
    • Markov Decision Processes
  • AI Planning
finite state dialogue management
Finite-State Dialogue Management
  • Consider a trivial airline travel system
    • Ask the user for a departure city
    • For a destination city
    • For a time
    • Whether the trip is round-trip or not
finite state dialogue managers
Finite-state Dialogue Managers
  • System completely controls the conversation with the user
  • Asks the user a series of questions
  • Ignores (or misinterprets) anything the user says that is not a direct answer to the system’s questions
dialogue initiative
Dialogue Initiative
  • Systems that control conversation like this are system initiative or single initiative.
  • “Initiative”: who has control of conversation
  • In normal human-human dialogue, initiative shifts back and forth between participants.
system initiative
System Initiative
  • Systems which completely control the conversation at all times are called system initiative.
  • Advantages:
    • Simple to build
    • User always knows what they can say next
    • System always knows what user can say next
      • Known words: Better performance from ASR
      • Known topic: Better performance from NLU
    • Ok for VERY simple tasks (entering a credit card, or login name and password)
  • Disadvantage:
    • Too limited
user initiative
User Initiative
  • User directs the system
  • Generally, user asks a single question, system answers
  • System can’t ask questions back, engage in clarification dialogue, confirmation dialogue
  • Used for simple database queries
  • User asks question, system gives answer
  • Web search is user initiative dialogue.
problems with system initiative
Problems with System Initiative
  • Real dialogue involves give and take!
  • In travel planning, users might want to say something that is not the direct answer to the question.
  • For example answering more than one question in a sentence:
    • Hi, I’d like to fly from Seattle Tuesday morning
    • I want a flight from Milwaukee to Orlando one way leaving after 5 p.m. on Wednesday.
single initiative universals
Single initiative + universals
  • We can give users a little more flexibility by adding universal commands
  • Universals: commands you can say anywhere
  • As if we augmented every state of FSA with these
    • Help
    • Start over
    • Correct
  • This describes many implemented systems
  • But still doesn’t allow user to say what the want to say
mixed initiative
Mixed Initiative
  • Conversational initiative can shift between system and user
  • Simplest kind of mixed initiative: use the structure of the frame itself to guide dialogue
    • Slot Question
    • ORIGIN What city are you leaving from?
    • DEST Where are you going?
    • DEPT DATE What day would you like to leave?
    • DEPT TIME What time would you like to leave?
    • AIRLINE What is your preferred airline?
frames are mixed initiative
Frames are mixed-initiative
  • User can answer multiple questions at once.
  • System asks questions of user, filling any slots that user specifies
  • When frame is filled, do database query
  • If user answers 3 questions at once, system has to fill slots and not ask these questions again!
  • Anyhow, we avoid the strict constraints on order of the finite-state architecture.
multiple frames
Multiple frames
  • flights, hotels, rental cars
  • Flight legs: Each flight can have multiple legs, which might need to be discussed separately
  • Presenting the flights (If there are multiple flights meeting users constraints)
    • It has slots like 1ST_FLIGHT or 2ND_FLIGHT so user can ask “how much is the second one”
  • General route information:
    • Which airlines fly from Boston to San Francisco
  • Airfare practices:
    • Do I have to stay over Saturday to get a decent airfare?
multiple frames1
Multiple Frames
  • Need to be able to switch from frame to frame
  • Based on what user says.
  • Disambiguate which slot of which frame an input is supposed to fill, then switch dialogue control to that frame.
  • Main implementation: production rules
    • Different types of inputs cause different productions to fire
    • Each of which can flexibly fill in different frames
    • Can also switch control to different frame
defining mixed initiative
Defining Mixed Initiative
  • Mixed Initiative could mean
    • User can arbitrarily take or give up initiative in various ways
      • This is really only possible in very complex plan-based dialogue systems
      • No commercial implementations
      • Important research area
    • Something simpler and quite specific which we will define in the next few slides
how mixed initiative is usually defined
How mixed initiative is usually defined
  • First we need to define two other factors
  • Open prompts vs. directive prompts
  • Restrictive versus non-restrictive grammar
open vs directive prompts
Open vs. Directive Prompts
  • Open prompt
    • System gives user very few constraints
    • User can respond how they please:
    • “How may I help you?” “How may I direct your call?”
  • Directive prompt
    • Explicit instructs user how to respond
    • “Say yes if you accept the call; otherwise, say no”
restrictive vs non restrictive grammars
Restrictive vs. Non-restrictive grammars
  • Restrictive grammar
    • Language model which strongly constrains the ASR system, based on dialogue state
  • Non-restrictive grammar
    • Open language model which is not restricted to a particular dialogue state
  • Voice eXtensible Markup Language
  • An XML-based dialogue design language
  • Makes use of ASR and TTS
  • Deals well with simple, frame-based mixed initiative dialogue.
  • Most common in commercial world (too limited for research systems)
  • But useful to get a handle on the concepts.
voice xml
Voice XML
  • Each dialogue is a <form>. (Form is the VoiceXML word for frame)
  • Each <form> generally consists of a sequence of <field>s, with other commands
sample vxml doc
Sample vxml doc


<field name="transporttype">


Please choose airline, hotel, or rental car. </prompt>

<grammar type="application/x=nuance-gsl">

[airline hotel "rental car"]





You have chosen <value expr="transporttype">. </prompt>



voicexml interpreter
VoiceXML interpreter
  • Walks through a VXML form in document order
  • Iteratively selecting each item
  • If multiple fields, visit each one in order.
  • Special commands for events
another vxml doc 1
Another vxml doc (1)


I'm sorry, I didn't hear you. <reprompt/>


- “noinput” means silence exceeds a timeout threshold


I'm sorry, I didn't understand that. <reprompt/>


- “nomatch” means confidence value for utterance is too low

- notice “reprompt” command

another vxml doc 2
Another vxml doc (2)


<block> Welcome to the air travel consultant. </block>

<field name="origin">

<prompt> Which city do you want to leave from? </prompt>

<grammar type="application/x=nuance-gsl">

[(san francisco) denver (new york) barcelona]



<prompt> OK, from <value expr="origin"> </prompt>



- “filled” tag is executed by interpreter as soon as field filled by user

another vxml doc 3
Another vxml doc (3)

<field name="destination">

<prompt> And which city do you want to go to? </prompt>

<grammar type="application/x=nuance-gsl">

[(san francisco) denver (new york) barcelona]



<prompt> OK, to <value expr="destination"> </prompt>



<field name="departdate" type="date">

<prompt> And what date do you want to leave? </prompt>


<prompt> OK, on <value expr="departdate"> </prompt>



another vxml doc 4
Another vxml doc (4)


<prompt> OK, I have you are departing from

<value expr="origin”> to <value expr="destination”> on <value expr="departdate">


send the info to book a flight...



summary voicexml
Summary: VoiceXML
  • Voice eXtensible Markup Language
  • An XML-based dialogue design language
  • Makes use of ASR and TTS
  • Deals well with simple, frame-based mixed initiative dialogue.
  • Most common in commercial world (too limited for research systems)
  • But useful to get a handle on the concepts.
information state and dialogue acts
Information-State and Dialogue Acts
  • If we want a dialogue system to be more than just form-filling
  • Needs to:
    • Decide when the user has asked a question, made a proposal, rejected a suggestion
    • Ground a user’s utterance, ask clarification questions, suggestion plans
  • Suggests:
    • Conversational agent needs sophisticated models of interpretation and generation
      • In terms of speech acts and grounding
      • Needs more sophisticated representation of dialogue context than just a list of slots
information state architecture
Information-state architecture
  • Information state
  • Dialogue act interpreter
  • Dialogue act generator
  • Set of update rules
    • Update dialogue state as acts are interpreted
    • Generate dialogue acts
  • Control structure to select which update rules to apply
dialogue acts
Dialogue acts
  • Also called “conversational moves”
  • An act with (internal) structure related specifically to its dialogue function
  • Incorporates ideas of grounding
  • Incorporates other dialogue and conversational functions that Austin and Searle didn’t seem interested in
verbmobil task
Verbmobil task
  • Two-party scheduling dialogues
  • Speakers were asked to plan a meeting at some future date
  • Data used to design conversational agents which would help with this task
  • (cross-language, translating, scheduling assistant)
verbmobil dialogue acts
Verbmobil Dialogue Acts

THANK thanks

GREET Hello Dan

INTRODUCE It’s me again

BYE Allright, bye

REQUEST-COMMENT How does that look?

SUGGEST June 13th through 17th

REJECT No, Friday I’m booked all day

ACCEPT Saturday sounds fine

REQUEST-SUGGEST What is a good day of the week for you?

INIT I wanted to make an appointment with you

GIVE_REASON Because I have meetings all afternoon


DELIBERATE Let me check my calendar here

CONFIRM Okay, that would be wonderful

CLARIFY Okay, do you mean Tuesday the 23rd?

automatic interpretation of dialogue acts
Automatic Interpretation of Dialogue Acts
  • How do we automatically identify dialogue acts?
  • Given an utterance:
    • Decide whether it is a QUESTION, STATEMENT, SUGGEST, or ACK
  • Recognizing illocutionary force will be crucial to building a dialogue agent
  • Perhaps we can just look at the form of the utterance to decide?
can we just use the surface syntactic form
Can we just use the surface syntactic form?
  • YES-NO-Q’s have auxiliary-before-subject syntax:
    • Will breakfast be served on USAir 1557?
  • STATEMENTs have declarative syntax:
    • I don’t care about lunch
  • COMMAND’s have imperative syntax:
    • Show me flights from Milwaukee to Orlando on Thursday night
dialogue act disambiguation is hard who s on first
Dialogue act disambiguation is hard! Who’s on First?

Abbott: Well, Costello, I'm going to New York with you. Bucky Harris the Yankee's manager gave me a job as coach for as long as you're on the team.

Costello: Look Abbott, if you're the coach, you must know all the players.

Abbott: I certainly do.

Costello: Well you know I've never met the guys. So you'll have to tell me their names, and then I'll know who's playing on the team.

Abbott: Oh, I'll tell you their names, but you know it seems to me they give these ball players now-a-days very peculiar names.

Costello: You mean funny names?

Abbott: Strange names, pet names...like Dizzy Dean...

Costello: His brother Daffy Abbott: Daffy Dean...

Costello: And their French cousin.

Abbott: French?

Costello: Goofe'

Abbott: Goofe' Dean. Well, let's see, we have on the bags, Who's on first, What's on second, I Don't Know is on third...

Costello: That's what I want to find out.

Abbott: I say Who's on first, What's on second, I Don't Know's on third.

dialogue act ambiguity
Dialogue act ambiguity
  • Who’s on first?
    • or
dialogue act ambiguity1
Dialogue Act ambiguity
  • Can you give me a list of the flights from Atlanta to Boston?
    • This looks like an INFO-REQUEST.
    • If so, the answer is:
      • YES.
    • But really it’s a DIRECTIVE or REQUEST, a polite form of:
    • Please give me a list of the flights…
  • What looks like a QUESTION can be a REQUEST
dialogue act ambiguity2
Dialogue Act ambiguity
  • Similarly, what looks like a STATEMENT can be a QUESTION:
indirect speech acts
Indirect speech acts
  • Utterances which use a surface statement to ask a question
  • Utterances which use a surface question to issue a request
da interpretation as statistical classification
DA interpretation as statistical classification
  • Lots of clues in each sentence that can tell us which DA it is:
  • Words and Collocations:
    • Please or would you: good cue for REQUEST
    • Are you: good cue for INFO-REQUEST
  • Prosody:
    • Rising pitch is a good cue for INFO-REQUEST
    • Loudness/stress can help distinguish yeah/AGREEMENT from yeah/BACKCHANNEL
  • Conversational Structure
    • Yeah following a proposal is probably AGREEMENT; yeah following an INFORM probably a BACKCHANNEL
statistical classifier model of dialogue act interpretation
Statistical classifier model of dialogue act interpretation
  • Our goal is to decide for each sentence what dialogue act it is
  • This is a classificationtask (we are making a 1-of-N classification decision for each sentence)
  • With N classes (= number of dialog acts).
  • Three probabilistic models corresponding to the 3 kinds of cues from the input sentence.
    • Conversational Structure: Probability of one dialogue act following another P(Answer|Question)
    • Words and Syntax: Probability of a sequence of words given a dialogue act: P(“do you” | Question)
    • Prosody: probability of prosodic features given a dialogue act : P(“rise at end of sentence” | Question)
an example of dialogue act detection correction detection
An example of dialogue act detection: Correction Detection
  • Despite all these clever confirmation/rejection strategies, dialogue systems still make mistakes (Surprise!)
  • If system misrecognizes an utterance, and either
    • Rejects
    • Via confirmation, displays its misunderstanding
  • Then user has a chance to make a correction
    • Repeat themselves
    • Rephrasing
    • Saying “no” to the confirmation question.
  • Unfortunately, corrections are harder to recognize than normal sentences!
    • Swerts et al (2000): corrections misrecognized twice as often (in terms of WER) as non-corrections!!!
    • Why?
      • Prosody seems to be largest factor: hyperarticulation
      • English Example from Liz Shriberg
        • “NO, I am DE-PAR-TING from Jacksonville)
      • A German example from Bettina Braun from a talking elevator
machine learning and classifiers
Machine Learning and Classifiers
  • Given a labeled training set
  • We can build a classifier to label observations into classes
    • Decision Tree
    • Regression
    • SVM
  • I won’t introduce the algorithms here.
  • But these are at the core of NLP/computational linguistics/Speech/Dialogue
  • You can learn them in:
    • AI - CS 121/221
    • Machine Learning CS 229
machine learning to detect user corrections
Machine learning to detect user corrections
  • Build classifiers using features like
    • Lexical information (words “no”, “correction”, “I don’t”, swear words)
    • Prosodic features (various increases in F0 range, pause duration, and word duration that correlation with hyperarticulation)
    • Length
    • ASR confidence
    • LM probability
    • Various dialogue features (repetition)
generating dialogue acts
Generating Dialogue Acts
  • Confirmation
  • Rejection
  • Another reason for grounding
  • Errors: Speech is a pretty errorful channel
    • Even for humans; so they use grounding to confirm that they heard correctly
  • ASR is way worse than humans!
  • So dialogue systems need to do even more grounding and confirmation than humans
explicit confirmation
Explicit confirmation
  • S: Which city do you want to leave from?
  • U: Baltimore
  • S: Do you want to leave from Baltimore?
  • U: Yes
explicit confirmation1
Explicit confirmation
  • U: I’d like to fly from Denver Colorado to New York City on September 21st in the morning on United Airlines
  • S: Let’s see then. I have you going from Denver Colorado to New York on September 21st. Is that correct?
  • U: Yes
implicit confirmation display
Implicit confirmation: display
  • U: I’d like to travel to Berlin
  • S: When do you want to travel to Berlin?
  • U: Hi I’d like to fly to Seattle Tuesday morning
  • S: Traveling to Seattle on Tuesday, August eleventh in the morning. Your name?
implicit vs explicit
Implicit vs. Explicit
  • Complementary strengths
  • Explicit: easier for users to correct systems’s mistakes (can just say “no”)
  • But explicit is cumbersome and long
  • Implicit: much more natural, quicker, simpler (if system guesses right).
implicit and explicit
Implicit and Explicit
  • Early systems: all-implicit or all-explicit
  • Modern systems: adaptive
  • How to decide?
    • ASR system can give confidence metric.
    • This expresses how convinced system is of its transcription of the speech
    • If high confidence, use implicit confirmation
    • If low confidence, use explicit confirmation
computing confidence
Computing confidence
  • Simplest: use acoustic log-likelihood of user’s utterance
  • More features
    • Prosodic: utterances with longer pauses, F0 excursions, longer durations
    • Backoff: did we have to backoff in the LM?
    • Cost of an error: Explicit confirmation before moving money or booking flights
  • e.g., VoiceXML “nomatch”
  • “I’m sorry, I didn’t understand that.”
  • Reject when:
    • ASR confidence is low
    • Best interpretation is semantically ill-formed
  • Might have four-tiered level of confidence:
    • Below confidence threshhold, reject
    • Above threshold, explicit confirmation
    • If even higher, implicit confirmation
    • Even higher, no confirmation
dialogue system evaluation
Dialogue System Evaluation
  • Key point about SLP.
  • Whenever we design a new algorithm or build a new application, need to evaluate it
  • Two kinds of evaluation
    • Extrinsic: embedded in some external task
    • Intrinsic: some sort of more local evaluation.
  • How to evaluate a dialogue system?
  • What constitutes success or failure for a dialogue system?
dialogue system evaluation1
Dialogue System Evaluation
  • It turns out we’ll need an evaluation metric for two reasons
    • 1) the normal reason: we need a metric to help us compare different implementations
      • can’t improve it if we don’t know where it fails
      • Can’t decide between two algorithms without a goodness metric
    • 2) a new reason: we will need a metric for “how good a dialogue went” as an input to reinforcement learning:
      • automatically improve our conversational agent performance via learning
evaluating dialogue systems
Evaluating Dialogue Systems
  • PARADISE framework (Walker et al ’00)
  • “Performance” of a dialogue system is affected both by whatgets accomplished by the user and the dialogue agent and howit gets accomplished


Task Success







Slide from Julia Hirschberg

paradise evaluation again
PARADISE evaluation again:
  • Maximize Task Success
  • Minimize Costs
    • Efficiency Measures
    • Quality Measures
  • PARADISE (PARAdigm for Dialogue System Evaluation)
task success
Task Success
  • % of subtasks completed
  • Correctness of each questions/answer/error msg
  • Correctness of total solution
    • Attribute-Value matrix (AVM)
    • Kappa coefficient
  • Users’ perception of whether task was completed
task success1
Task Success
  • Task goals seen as Attribute-Value Matrix
      • ELVIS e-mail retrieval task(Walker et al ‘97)
      • “Find the time and place of your meeting with Kim.”

Attribute Value

Selection Criterion Kim or Meeting

Time 10:30 a.m.

Place 2D516

  • Task success can be defined by match between AVM values at end of task with “true” values for AVM

Slide from Julia Hirschberg

efficiency cost
Efficiency Cost
  • Polifroni et al. (1992), Danieli and Gerbino (1995) Hirschman and Pao (1993)
  • Total elapsed time in seconds or turns
  • Number of queries
  • Turn correction ration: number of system or user turns used solely to correct errors, divided by total number of turns
quality cost
Quality Cost
  • # of times ASR system failed to return any sentence
  • # of ASR rejection prompts
  • # of times user had to barge-in
  • # of time-out prompts
  • Inappropriateness (verbose, ambiguous) of system’s questions, answers, error messages
another key quality cost
Another key quality cost
  • “Concept accuracy” or “Concept error rate”
  • % of semantic concepts that the NLU component returns correctly
  • I want to arrive in Austin at 5:00
    • DESTCITY: Boston
    • Time: 5:00
  • Concept accuracy = 50%
  • Average this across entire dialogue
  • “How many of the sentences did the system understand correctly”
regressing against user satisfaction
Regressing against user satisfaction
  • Questionnaire to assign each dialogue a “user satisfaction rating”: this is dependent measure
  • Set of cost and success factors are independent measures
  • Use regression to train weights for each factor
experimental procedures
Experimental Procedures
  • Subjects given specified tasks
  • Spoken dialogues recorded
  • Cost factors, states, dialog acts automatically logged; ASR accuracy,barge-in hand-labeled
  • Users specify task solution via web page
  • Users complete User Satisfaction surveys
  • Use multiple linear regression to model User Satisfaction as a function of Task Success and Costs; test for significant predictive factors

Slide from Julia Hirschberg

user satisfaction sum of many measures
Was the system easy to understand? (TTS Performance)

Did the system understand what you said? (ASR Performance)

Was it easy to find the message/plane/train you wanted? (Task Ease)

Was the pace of interaction with the system appropriate? (Interaction Pace)

Did you know what you could say at each point of the dialog? (User Expertise)

How often was the system sluggish and slow to reply to you? (System Response)

Did the system work the way you expected it to in this conversation? (Expected Behavior)

Do you think you'd use the system regularly in the future? (Future Use)

User Satisfaction:Sum of Many Measures

Adapted from Julia Hirschberg

performance functions from three systems
Performance Functions from Three Systems
  • ELVIS User Sat.= .21* COMP + .47 * MRS - .15 * ET
  • TOOT User Sat.= .35* COMP + .45* MRS - .14*ET
  • ANNIE User Sat.= .33*COMP + .25* MRS +.33* Help
    • COMP: User perception of task completion (task success)
    • MRS: Mean (concept) recognition accuracy (cost)
    • ET: Elapsed time (cost)
    • Help: Help requests (cost)

Slide from Julia Hirschberg

performance model
Performance Model
  • Perceived task completion and mean recognition score (concept accuracy) are consistently significant predictors of User Satisfaction
  • Performance model useful for system development
    • Making predictions about system modifications
    • Distinguishing ‘good’ dialogues from ‘bad’ dialogues
    • As part of a learning model
now that we have a success metric
Now that we have a success metric
  • Could we use it to help drive learning?
  • In recent work we use this metric to help us learn an optimal policy or strategy for how the conversational agent should behave
new idea modeling a dialogue system as a probabilistic agent
New Idea: Modeling a dialogue system as a probabilistic agent
  • A conversational agent can be characterized by:
    • The current knowledge of the system
      • A set of statesS the agent can be in
    • a set of actionsA the agent can take
    • A goalG, which implies
      • A success metric that tells us how well the agent achieved its goal
      • A way of using this metric to create a strategy or policy for what action to take in any particular state.
what do we mean by actions a and policies
What do we mean by actions A and policies ?
  • Kinds of decisions a conversational agent needs to make:
    • When should I ground/confirm/reject/ask for clarification on what the user just said?
    • When should I ask a directive prompt, when an open prompt?
    • When should I use user, system, or mixed initiative?
a threshold is a human designed policy
A threshold is a human-designed policy!
  • Could we learn what the right action is
    • Rejection
    • Explicit confirmation
    • Implicit confirmation
    • No confirmation
  • By learning a policy which,
    • given various information about the current state,
    • dynamically chooses the action which maximizes dialogue success
another strategy decision
Another strategy decision
  • Open versus directive prompts
  • When to do mixed initiative
  • The Linguistics of Conversation
  • Basic Conversational Agents
    • ASR
    • NLU
    • Generation
    • Dialogue Manager
  • Dialogue Manager Design
    • Finite State
    • Frame-based
    • Initiative: User, System, Mixed
  • VoiceXML
  • Information-State
    • Dialogue-Act Detection
    • Dialogue-Act Generation
  • Evaluation
  • Utility-based conversational agents
    • MDP, POMDP
end of today s lecture
review open vs directive prompts
Review: Open vs. Directive Prompts
  • Open prompt
    • System gives user very few constraints
    • User can respond how they please:
    • “How may I help you?” “How may I direct your call?”
  • Directive prompt
    • Explicit instructs user how to respond
    • “Say yes if you accept the call; otherwise, say no”
review restrictive vs non restrictive gramamrs
Review: Restrictive vs. Non-restrictive gramamrs
  • Restrictive grammar
    • Language model which strongly constrains the ASR system, based on dialogue state
  • Non-restrictive grammar
    • Open language model which is not restricted to a particular dialogue state
kinds of initiative
Kinds of Initiative
  • How do I decide which of these initiatives to use at each point in the dialogue?
modeling a dialogue system as a probabilistic agent
Modeling a dialogue system as a probabilistic agent
  • A conversational agent can be characterized by:
    • The current knowledge of the system
      • A set of statesS the agent can be in
    • a set of actionsA the agent can take
    • A goalG, which implies
      • A success metric that tells us how well the agent achieved its goal
      • A way of using this metric to create a strategy or policy for what action to take in any particular state.
goals are not enough
Goals are not enough
  • Goal: user satisfaction
  • OK, that’s all very well, but
    • Many things influence user satisfaction
    • We don’t know user satisfaction til after the dialogue is done
    • How do we know, state by state and action by action, what the agent should do?
  • We need a more helpful metric that can apply to each state
  • A utility function
    • maps a state or state sequence
    • onto a real number
    • describing the goodness of that state
    • I.e. the resulting “happiness” of the agent
  • Principle of Maximum Expected Utility:
    • A rational agent should choose an action that maximizes the agent’s expected utility
maximum expected utility
Maximum Expected Utility
  • Principle of Maximum Expected Utility:
    • A rational agent should choose an action that maximizes the agent’s expected utility
  • Action A has possible outcome states Resulti(A)
  • E: agent’s evidence about current state of world
  • Before doing A, agent estimates prob of each outcome
    • P(Resulti(A)|Do(A),E)
  • Thus can compute expected utility:
markov decision processes
Markov Decision Processes
  • Or MDP
  • Characterized by:
    • a set of states S an agent can be in
    • a set of actions A the agent can take
    • A reward r(a,s) that the agent receives for taking an action in a state
    • (+ Some other things I’ll come back to (gamma, state transition probabilities))
a brief tutorial example
A brief tutorial example
  • Levin et al (2000)
  • A Day-and-Month dialogue system
  • Goal: fill in a two-slot frame:
    • Month: November
    • Day: 12th
  • Via the shortest possible interaction with user
what is a state
What is a state?
  • In principle, MDP state could include any possible information about dialogue
    • Complete dialogue history so far
  • Usually use a much more limited set
    • Values of slots in current frame
    • Most recent question asked to user
    • Users most recent answer
    • ASR confidence
    • etc
state in the day and month example
State in the Day-and-Month example
  • Values of the two slots day and month.
  • Total:
    • 2 special initial state si and sf.
    • 365 states with a day and month
    • 1 state for leap year
    • 12 states with a month but no day
    • 31 states with a day but no month
    • 411 total states
actions in mdp models of dialogue
Actions in MDP models of dialogue
  • Speech acts!
    • Ask a question
    • Explicit confirmation
    • Rejection
    • Give the user some database information
    • Tell the user their choices
  • Do a database query
actions in the day and month example
Actions in the Day-and-Month example
  • ad: a question asking for the day
  • am: a question asking for the month
  • adm: a question asking for the day+month
  • af: a final action submitting the form and terminating the dialogue
a simple reward function
A simple reward function
  • For this example, let’s use a cost function
  • A cost function for entire dialogue
  • Let
    • Ni=number of interactions (duration of dialogue)
    • Ne=number of errors in the obtained values (0-2)
    • Nf=expected distance from goal
      • (0 for complete date, 1 if either data or month are missing, 2 if both missing)
  • Then (weighted) cost is:
  • C = wiNi + weNe + wfNf
3 possible policies
3 possible policies


P1=probability of error in open prompt

Open prompt

Directive prompt

P2=probability of error in directive prompt

3 possible policies1
3 possible policies

Strategy 3 is better than strategy 2 when

improved error rate justifies longer interaction:

P1=probability of error in open prompt


P2=probability of error in directive prompt


that was an easy optimization
That was an easy optimization
  • Only two actions, only tiny # of policies
  • In general, number of actions, states, policies is quite large
  • So finding optimal policy * is harder
  • We need reinforcement leraning
  • Back to MDPs:
  • We can think of a dialogue as a trajectory in state space
  • The best policy * is the one with the greatest expected reward over all trajectories
  • How to compute a reward for a state sequence?
reward for a state sequence
Reward for a state sequence
  • One common approach: discounted rewards
  • Cumulative reward Q of a sequence is discounted sum of utilities of individual states
  • Discount factor  between 0 and 1
  • Makes agent care more about current than future rewards; the more future a reward, the more discounted its value
the markov assumption
The Markov assumption
  • MDP assumes that state transitions are Markovian
expected reward for an action
Expected reward for an action
  • Expected cumulative reward Q(s,a) for taking a particular action from a particular state can be computed by Bellman equation:
  • Expected cumulative reward for a given state/action pair is:
    • immediate reward for current state
    • + expected discounted utility of all possible next states s’
    • Weighted by probability of moving to that state s’
    • And assuming once there we take optimal action a’
what we need for bellman equation
What we need for Bellman equation
  • A model of p(s’|s,a)
  • Estimate of R(s,a)
  • How to get these?
  • If we had labeled training data
    • P(s’|s,a) = C(s,s’,a)/C(s,a)
  • If we knew the final reward for whole dialogue R(s1,a1,s2,a2,…,sn)
  • Given these parameters, can use value iteration algorithm to learn Q values (pushing back reward values over state sequences) and hence best policy
final reward
Final reward
  • What is the final reward for whole dialogue R(s1,a1,s2,a2,…,sn)?
  • This is what our automatic evaluation metric PARADISE computes!
  • The general goodness of a whole dialogue!!!!!
how to estimate p s s a without labeled data
How to estimate p(s’|s,a) without labeled data
  • Have random conversations with real people
    • Carefully hand-tune small number of states and policies
    • Then can build a dialogue system which explores state space by generating a few hundred random conversations with real humans
    • Set probabilities from this corpus
  • Have random conversations with simulated people
    • Now you can have millions of conversations with simulated people
    • So you can have a slightly larger state space
an example
An example
  • Singh, S., D. Litman, M. Kearns, and M. Walker. 2002. Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. Journal of AI Research.
  • NJFun system, people asked questions about recreational activities in New Jersey
  • Idea of paper: use reinforcement learning to make a small set of optimal policy decisions
very small of states and acts
Very small # of states and acts
  • States: specified by values of 8 features
    • Which slot in frame is being worked on (1-4)
    • ASR confidence value (0-5)
    • How many times a current slot question had been asked
    • Restrictive vs. non-restrictive grammar
    • Result: 62 states
  • Actions: each state only 2 possible actions
    • Asking questions: System versus user initiative
    • Receiving answers: explicit versus no confirmation.
ran system with real users
Ran system with real users
  • 311 conversations
  • Simple binary reward function
    • 1 if competed task (finding museums, theater, winetasting in NJ area)
    • 0 if not
  • System learned good dialogue strategy: Roughly
    • Start with user initiative
    • Backoff to mixed or system initiative when re-asking for an attribute
    • Confirm only a lower confidence values
state of the art
State of the art
  • Only a few such systems
    • From (former) ATT Laboratories researchers, now dispersed
    • And Cambridge UK lab
  • Hot topics:
    • Partially observable MDPs (POMDPs)
    • We don’t REALLY know the user’s state (we only know what we THOUGHT the user said)
    • So need to take actions based on our BELIEF , I.e. a probability distribution over states rather than the “true state”