Discourse Structure in Generation Julia Hirschberg CS 4706 12/6/2018
Today Models of Discourse Structure Do we have them? Grosz & Sidner ’86 What identifies discourse structure to Hearers? Textual cues Spoken cues How can we produce appropriate discourse structure in TTS systems? Can we identify discourse structure automatically, from speech? 12/6/2018
Is there structure in this discourse? A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
Is this a reasonable structure? A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
This? A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
This? A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
What information do we use in segmenting a discourse? ‘Topic’ coherence? Repeated reference? ‘Cue’ phrases? ???? 12/6/2018
Structures of Discourse Structure (Grosz & Sidner ‘86) A leading theory of discourse structure Based upon Speaker intentions and Speaker and Hearer attentional state Identifies a few, general relations that hold among Speaker intentions Identifies a model of attentional state Three components: Linguistic structure Intentional structure Attentional structure 12/6/2018
Linguistic Structure What is actually said or written How is the linguistic structure represented? Assume discourse is segmented into Discourse Segments (DS) What is the basic unit of analysis? Do we all segment alike? Do we all use the same cues? 12/6/2018
Linguistic Structure of Discourse D S1: A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. S2: Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
Intentional Structure Discourse purpose (DP): basic purpose of the Speaker in producing the discourse Discourse segment purposes (DSPs): the Speaker’s purpose in producing the segment Segments are related to one another by their purposes: Satisfaction-precedence: DSP1 must be satisfied before DSP2 Dominance: DSP1 dominates DSP2 if fulfilling DSP2 constitutes part of fulfilling DSP1 12/6/2018
Linguistic Structure of Discourse D DSP1: Describe murder of dove by duck. S1: A beautiful mallard spotted the dove I was feeding. The duck dove supply is small this year. That dove was history in a minute. DSP2: Describe meeting of old friend. S2: Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. To my surprise, I ran into a friend from back home. When I told her of my recent experience she questioned my sanity. 12/6/2018
DSP2: Describe recovery process. S2: DSP3: Describe snack S3: Well, to recover from this horrible scene, I went to the park snack bar for a cup of cocoa. DSP3: Describe meeting old friend. S4: To my surprise, I ran into a friend from back home. DSP5: Describe friend’s reaction S5: When I told her of my recent experience she questioned my sanity. 12/6/2018
Attentional State: The Focus Stack Stack of focus spaces, each containing objects, properties and relations salient during each DS, plus the DSP State changes: transition rules controlling the addition/deletion of focus spaces Information at lower levels may or may not be available at higher levels Focus spaces are pushed onto the stack when A new DS is begun 12/6/2018
Focus spaces are popped when they are completed An embedded DS (e.g. a DS dominated by another DS) is begun Focus spaces are popped when they are completed State of focus stack models felicitous reference, coherence in discourse S2: DSP2, scene, Speaker, snack_bar Cocoa, friend, home,sanity S1: DSP1, duck, dove, Speaker, duck_dove_supply 12/6/2018
Limits of the Theory Assumes discourses are task-oriented Assumes a single, hierarchical structure shared by S and H Questions: Do people really build such structures when they converse? Use them in interpreting what others say? How could they do it? 12/6/2018
How might people recognize discourse structure? Linguistic markers? tense and aspect cue phrases Inference of Speaker intentions? Inference from task structure? Intonational Information? 12/6/2018
Acoustic and Prosodic Cues to Discourse Structure Intuition: Speakers vary acoustic and prosodic cues to convey variation in discourse structure Systematic? In read or spontaneous speech? Evidence: Observations from recorded corpora Laboratory experiments Machine learning of discourse structure from acoustic/prosodic features 12/6/2018
Prosodic Correlates of Discourse/Topic Structure Pitch range Lehiste ’75, Brown et al ’83, Silverman ’86, Avesani & Vayra ’88, Ayers ’92, Swerts et al ’92, Grosz & Hirschberg’92, Swerts & Ostendorf ’95, Hirschberg & Nakatani ‘96 Preceding pause Lehiste ’79, Chafe ’80, Brown et al ’83, Silverman ’86, Woodbury ’87, Avesani & Vayra ’88, Grosz & Hirschberg’92, Passoneau & Litman ’93, Hirschberg & Nakatani ‘96 12/6/2018
Brown et al ’83, Grosz & Hirschberg’92, Hirschberg & Nakatani ‘96 Rate Butterworth ’75, Lehiste ’80, Grosz & Hirschberg’92, Hirschberg & Nakatani ‘96 Amplitude Brown et al ’83, Grosz & Hirschberg’92, Hirschberg & Nakatani ‘96 Contour Brown et al ’83, Woodbury ’87, Swerts et al ‘92 Add Audix tree?? 12/6/2018
Issues Do we find significant and reliable cues to discourse structure in prosodic variation When tested against an independent theory of discourse structure? In spontaneous as well as read speech? Are Hearers interpretations of discourse structure influenced by intonational variation? 12/6/2018
Grosz & Hirschberg ‘92 Small corpus of read AP newswire Read by professional speaker Labeled for discourse structure from text alone or from text and speech Pre-ToBI labeled Acoustic-prosodic features extracted for each intermediate (level 3) phrase Pitch range and change from prior phrase Intensity (rms) and change in db from prior phrase Preceding and subsequent pause Speaking rate 12/6/2018
ANOVA’s and t-tests on means Results: Analysis of phrases in different segment positions: SBEG, SF, parentheticals, quoted speech ANOVA’s and t-tests on means Results: Direct quotes: larger pitch range Parentheticals: smaller range, neg change from prior phrase, neg change in db, faster rate SBEG: larger range, louder, greater preceding pause, less subsequent pause SF: greater subsequent pause 12/6/2018
Machine learning experiments identified: SBEG with 91.5% est. accuracy (x-validation) SF, 92.5% Attributive tags, 96.9% Direct quotations, 86.4% Indirect quotations, 88.5% Parentheticals, 89.2% Conclusion: Acoustic/prosodic information is available to permit Hearers to identify discourse structure… 12/6/2018
Next The midterm Closed book, no notes or electronic devices Will include material through today 12/6/2018