Dialogue Systems Julia Hirschberg CS 4705 7/15/2016 1 Today • Examples from English and Swedish • Controlling the dialogue flow – State prediction • Controlling user behavior: Entrainment • Learning from human-human dialogue – User feedback • Evaluating systems 7/15/2016 2 Amtrak’s Julie • It would be funny if it weren’t so true… • http://www.cs.columbia.edu/~julia/tmp/SpeechR ecoDate.wmv 7/15/2016 3 Issues in Designing SDS • Coverage: functionality and vocabulary • Dialogue control: – System – User – Mixed initiative • Confirmation strategies: – Explicit – Implicit – None 7/15/2016 4 The Waxholm Project at KTH • tourist information • Stockholm archipelago • time-tables, hotels, hostels, camping and dining possibilities. • mixed initiative dialogue • speech recognition • multimodal synthesis • graphic information • pictures, maps, charts and time-tables • Demos at http://www.speech.kth.se/multimodal 7/15/2016 5 The Waxholm system 7/15/2016 There Information Information Information Which areWhen IIs IWaxholm am lots Which think day This itWhere looking possible of Ido about about Where of want about is Iboats hotels the want the Thank ais can Thank table hotels the evening to The for week shown to the from isto go are Ieat restaurants boats Waxholm? you find city hotels of go tomorrow you is in do Stockholm in the to on boats shown too Waxholm? hotels? Waxholm? you to Waxholm boats... this inWaxholm Waxholm want depart? in map inWaxholm to this toWaxholm go? table is on a Friday, Fromis At shown where shown whatin do time inthis you this do table want table you to want go to go? 6 Dialogue control state prediction Dialog grammar specified by a number of states Each state associated with an action database search, system question… … Probable state determined from semantic features Transition probability from one state to state Dialog control design tool with a graphic interface 7/15/2016 7 Waxholm Topics TIME_TABLE Task: get a time-table. Example: När går båten? (When does the boat leave?) SHOW_MAP Task : get a chart or a map displayed. Example: Var ligger Vaxholm? (Where is Vaxholm located?) EXIST Task : display lodging and dining possibilities. Example: Var finns det vandrarhem? (Where are there hostels?) OUT_OF_DOMAIN Task : the subject is out of the domain. Example: Kan jag boka rum. (Can I book a room?) NO_UNDERSTANDING Task : no understanding of user intentions. Example: Jag heter Olle. (My name is Olle) END_SCENARIO Task : end a dialog. Example: Tack. (Thank you.) 7/15/2016 8 Topic selection FEATURES 7/15/2016 TOPIC EXAMPLES TIME TABLE SHOW MAP FACILITY NO UNDER- OUT OF STANDING DOMAIN OBJECT QUEST-WHEN QUEST-WHERE FROM-PLACE AT-PLACE .062 .188 .062 .250 .062 .312 .031 .688 .031 .219 .073 .024 .390 .024 .293 .091 .091 .091 .091 .091 .067 .067 .067 .067 .067 .091 .091 .091 .091 .091 TIME PLACE OOD END HOTEL HOSTEL ISLAND PORT MOVE .312 .091 .062 .062 .062 .062 .333 .125 .875 .031 .200 .031 .031 .031 .031 .556 .750 .031 .024 .500 .122 .024 .488 .122 .062 .244 .098 .091 .091 .091 .091 .091 .091 .091 .091 .091 .067 .067 .933 .067 .067 .067 .067 .067 .067 .091 .091 .091 .909 .091 .091 .091 .091 .091 { p(ti | F )} argmax i END 9 Topic prediction results % Errors 15 12,9 8,8 10 5 12,7 8,5 All “no understanding” excluded 3,1 2,9 0 complete parse 7/15/2016 raw data no extra linguistic sounds 10 Entrainment • Conversationalists entrain to each other – Lexically (Clark ’89,Clark & Brennan ’96) • Conceptual pacts “the extraterrestrial” vs. “the alien” – Acoustically and prosodically • Adaptation/accommodation to speaking rate, rhythm, amplitude, pitch range – General speaking style • The Emperor of Japan (Azuma ’97) • Turn-taking (when speaking to a robot) (Breazeal ’02) 7/15/2016 11 Uses in SDS: To Encourage Users to Employ System Vocabulary The answers to the question: “What weekday do you want to go?” (Vilken veckodag vill du åka?) • • • • • 22% 11% 11% 7% 6% • - 7/15/2016 Friday (fredag) I want to go on Friday (jag vill åka på fredag) I want to go today (jag vill åka idag) on Friday (på fredag) I want to go a Friday (jag vill åka en fredag) are there any hotels in Vaxholm? (finns det några hotell i Vaxholm) 12 Examples of questions and answers Hur ofta åker du utomlands på semestern? Hur ofta reser du utomlands på semestern? jag åker en gång om året kanske jag åker ganska sällan utomlands på semester jag åker nästan alltid utomlands under min semester jag åker ungefär 2 gånger per år utomlands på semester jag åker utomlands nästan varje år jag åker utomlands på semestern varje år jag åker utomlands ungefär en gång om året jag är nästan aldrig utomlands en eller två gånger om året en gång per semester kanske en gång per år ungefär en gång per år åtminståne en gång om året nästan aldrig 7/15/2016 jag reser en gång om året utomlands jag reser inte ofta utomlands på semester det blir mera i arbetet jag reser reser utomlands på semestern vartannat år jag reser utomlands en gång per semester jag reser utomlands på semester ungefär en gång per år jag brukar resa utomlands på semestern åtminståne en gång i året en gång per år kanske en gång vart annat år varje år vart tredje år ungefär nu för tiden inte så ofta varje år brukar jag åka utomlands 13 Results no no reuse 4% 2%answer other 24% reuse 52% 18% ellipse 7/15/2016 14 Evidence from Human Performance • Users provide explicit positive and negative feedback • Corpus-based vs. laboratory experiments – do these tell us different things? 7/15/2016 15 The August system 7/15/2016 People IWhat IStrindberg IYes, Over call The can How come Strindberg The Perhaps myself answer that information who amany from Royal million was live we Strindberg, questions the was people Institute ain will people smart glass married ishere? shown live thing about of houses live but in I Yes, When it What Do You do might you Thank you Good were are is was like your be do welcome! bye! you that you! born for itdepartment name? born? we ameet inliving? will! 1849 Strindberg, ofdon’t Speech, should in the really three Technology! Stockholm? on soon Stockholm not KTH Music tothe have throw say! times! again! map and and a surname Stockholm stones area Hearing 16 Adapt – demonstration of ”complete” system 7/15/2016 17 Feedback and ‘Grounding’: Bell & Gustafson ’00 • Positive and negative – Previous corpora: August system • 18% of users gave pos or neg feedback in subcorpus • Push-to-talk • Corpus: Adapt system – 50 dialogues, 33 subjects, 1845 utterances – Feedback utterances labeled w/ • Positive or negative • Explicit or implicit • Attention/Attitude • Results: – 18% of utterances contained feedback – 94% of users provided 7/15/2016 18 – 65% positive, 2/3 explicit, equal amounts of attention vs. attitude – Large variation • Some subjects provided at almost every turn • Some never did • Utility of study: – Use positive feedback to model the user better (preferences) – Use negative feedback in error detection 7/15/2016 19 The HIGGINS domain This is a 3D test environment • • The primary domain of HIGGINS is city navigation for pedestrians. Secondarily, HIGGINS is intended to provide simple information about the immediate surroundings. 7/15/2016 20 Initial experiments • Studies on human-human conversation • The Higgins domain (similar to Map Task) • Using ASR in one direction to elicit error handling behaviour User 7/15/2016 Speaks ASR Listens Vocoder Reads Speaks Operator 21 Non-Understanding Error Recovery (Skantze ’03) • Humans tend not to signal non-understanding: – O: Do you see a wooden house in front of you? – U: ASR: YES CROSSING ADDRESS NOW (I pass the wooden house now) – O: Can you see a restaurant sign? • This leads to – Increased experience of task success – Faster recovery from non-understanding 7/15/2016 22 Evaluating Dialogue Systems • PARADISE framework (Walker et al ’00) • “Performance” of a dialogue system is affected both by what gets accomplished by the user and the dialogue agent and how it gets accomplished Maximize Task Success Minimize Costs Efficiency Measures 7/15/2016 Qualitative Measures 23 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 Selection Criterion Time Place Value Kim or Meeting 10:30 a.m. 2D516 •Task success defined by match between AVM values at end of with “true” values for AVM 7/15/2016 24 Metrics • Efficiency of the Interaction:User Turns, System Turns, Elapsed Time • Quality of the Interaction: ASR rejections, Time Out Prompts, Help Requests, Barge-Ins, Mean Recognition Score (concept accuracy), Cancellation Requests • User Satisfaction • Task Success: perceived completion, information extracted 7/15/2016 25 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 7/15/2016 26 User Satisfaction: Sum of Many Measures • Was Annie easy to understand in this conversation? (TTS Performance) • In this conversation, did Annie understand what you said? (ASR Performance) • In this conversation, was it easy to find the message you wanted? (Task Ease) • Was the pace of interaction with Annie appropriate in this conversation? (Interaction Pace) • In this conversation, did you know what you could say at each point of the dialog? 7/15/2016 (User Expertise) • How often was Annie sluggish and slow to reply to you in this conversation? (System Response) • Did Annie work the way you expected her to in this conversation? (Expected Behavior) • From your current experience with using Annie to get your email, do you think you'd use Annie regularly to access your mail when you are away from your desk? (Future Use) 27 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 recognition accuracy (cost) – ET: Elapsed time (cost) – Help: Help requests (cost) 7/15/2016 28 Performance Model • Perceived task completion and mean recognition score are consistently significant predictors of User Satisfaction • Performance model useful for system development – Making predictions about system modifications – Distinguishing ‘good’ dialogues from ‘bad’ dialogues • But can we also tell on-line when a dialogue is ‘going wrong’ 7/15/2016 29 Next • Story Generation (David Elson) 7/15/2016 30