What

1
Whats New?

• Discourse Dialogue
• CMSC 35900-1
• October 28, 2004

2
Agenda

• Attention and Information
• Given/New dichotomy
• Implications Applications
• Given/New-based paraphrase
• Speech recognition synthesis
• Stress and accent
• Gestural synthesis

3
Discourse

• So far
• Analytic models (GS,MT)
• Discourse structure recognition, segmentation
• Now, generation and synthesis
• Sentence/paragraph surface realization
• Grammatical forms of discourse entities pron,
  def NP
• Sentence ordering of information subj/not
• Acoustic form of entities- accented/not accent
  type

4
Attention and Information

• Perspective Focus of Attention
• Coherence, Reference
• Perspective Information Flow
• Goal of discourse
• Communication of information
• Speaker to hearer

5
Given/New Dichotomy

• Each information unit contains
• New information
• the News
• New to hearer
• New to discourse
• Given/Old information
• What is being talked about
• Known to hearer
• Already evoked in discourse

6
Given/New Effects

• Influences structure of utterance
• Word order
• Form of referring expression
• Prosodic prominence
• Guides interpretation by hearer

7
Given/New Word Order

• Default word order (English, declarative)
• Left-to-right increase in New-ness
• Subject -gt Given
• Discourse-old - present in context
• Predicate -gt New

8
Given/New Referring Expressions

• Hierarchy of salience
• Tied to Given/New status
• GivenSalient -gt Pronoun
• Given, less salient -gt Definite NP
• New -gt Indefinite NP

9
Given/New Prosody

• Prosody
• Pitch, Loudness, Duration,
• Tone group Information Unit
• Given New
• Unstressed -gt Given, salient
• Stressed -gt New, less salient

10
Application of Information Flow

• Paraphrase (McKeown 1983)
• Natural language is ambiguous
• Semantic - word senses - e.g. bank
• Syntactic - structural
• E.g. prepositional phrase attachment
• Reference
• Paraphrase makes explicit system interpretation
• Especially modification

11
Given/New Perspective

• Word order affected by role in sentence
• What speaker thinks hearer knows or not
• Wh-items are new, rest given, assume true
• Question 3 parts
• 2Lack of knowledge wh-item with no subclause
• 3Angle Direct/Indirect modifiers of wh-items
• 1Given info Everything else

12
Example

• Q Which active users advised by Tom Wirth work
  on projects in area 3?
• P Assuming that there are projects in area 3,
  which active users work on those projects? Look
  for users advised by Wirth.

New lack info
Work on
Active users
projects
New Angle
Advised by TW
Given
In area 3
13
Syntax Information Structure

• Link parse tree to Given/new info
• Root Main verb Inorder traversal
• Left subtree Subject Preorder
• Right subtree Object Preorder
• Traversal order Part informationTransform
• gt Linearization

14
Paraphrase by Given/New

• Advantages
• Corrective response e.g. if given info isnt
• More flexible/portable that template-based
  paraphrase

15
Applications of Info Structure

• Speech recognition and synthesis
• Prosody
• Pitch, loudness, length
• New - more likely stressed Old often unstressed
• Tunes for given/new

16
Understanding Acoustic Realization

• Motivation
• Synthetic speech
• Experimental evidence
• Key components
• Prosody
• Syntax
• Contextually appropriate speech synthesis

17
Speech Synthesis

• Generally INTELLIGIBLE
• But not NATURAL
• Requires high attention to listen to
• Default sentence intonation
• May be misleading
• Speaking of BILL,
• A) JOHN thought he would WIN, but he DIDNT
• B) JOHN thought he would WIN, but HE didnt

18
Accent Assignment Analysis

• Accent
• Increased loudness, duration, pitch movement
• Basic view
• available/Given no accent New(er) accent
• Attend to new information
• Questions
• Does accent continue to decrease with repetition?
• How does discourse structure affect accent?

19
Accent Assignment Results

• Topic status First/Later mention vs
• De-/Accenting, form of referring expression
• Results
• First,Topic Accented, Full NP
• Later,Topic De-accented , probably pronoun
• Later,Topic,Refinement Accented (even Pron)
• First,-Topic Accented Full NP
• Later,-Topic Accented Full NP, Implicit
• Later,-Topic,past-topic/contrast Accented NP
  (mod)

20
ToBI Intonation Framework

• ToBI Tone and Break Indices
• Describe English sentence intonation
• Tones
• Two pitch levels H(igh) and L(ow)
• - on stressed syllable, e.g. H, L, LH
• Types Pitch accents, Phrase Tones (L-,L)
• Last accent in phrase nuclear accent
• Units Intermediate and Intonational Phrases

21
ToBI Intonation Framework

• Break indices
• Mark groupings in speech
• 0 - most closely linked 5 - most disjoint
• 4 Intermediate phrase boundary (-)
• comma
• 5 Intonational phrase boundary (,)
• period - sentence

22
ToBI Examples
23
Contrast Examples
24
Contrast Examples
25
Contrast Examples
26
Syntax Information Status

• Intonation units more flexible than standard
  syntactic constituents, e.g. subject, predicate
• CCG - Combinatory Categorial Grammar
• Allows multiple analyses (parses) to fit
• Link syntactic, semantic, and pragmatic/prosodic
  function with each unit

27
Generating Appropriate Intonation

• Basic previous mention strategy
• Accent first mention of content words
• De-accent closed class function words
• De-accent content words already mentioned
• Inadequate
• Need contrastive stress TOO

28
Generating Appropriate Intonation

• Identify theme (topic links to previous info)
• Identify rheme (contributes new information)
• Shared propositional content
• Assign appropriate basic intonation contour
• rhemeH L-L
• themeLH L-H (at most)

29
Generating Appropriate Intonation

• Identify focus element in theme/rheme
• Word to get accent
• Focus
• First mention, and
• Contrastive
• What is contrastive????

30
Contrastive Items Domain

• For each entity x
• 0 find alternatives in discourse and KB
• 1 RSET x and alternatives,
• PROPS features of x
• CSET features of x to mark for contrast
• 2 For each p in PROPS, r in RSET,
• IF p is not property of r, add p to CSET.
• 3 Focus p of x
• E.g. She broke her left LEG, NOT her RIGHT leg.

31
Contrastive Items WordNet

• WordNet Semantic KB
• 4 parts of speech N,V,Adj, Adv
• Category/word one or more synonym sets
• Hierarchies linked by relations e.g. IS-A
• Content Word W is new if NOT
• In focus history or historys equivalence class
• Equiv. Class reachable by N hypernym/synset
  links
• Content Word W is contrastive if
• In historys contrast list
• Contrast hyponyms of hypernyms of W

32
Examples

• (84) Q I know which AMPLIFIER produces clean
  BASS,
• but WHICH amplifier produces clean TREBLE?
• LH L(H)
  H LL
• A The BRITISH amplifier produces clean TREBLE.
• H L(L)
  LH LH
• (85) Q I know which AMPLIFIER produces MUDDY
  treble,
• but WHICH amplifier produces CLEAN treble?
• LH L(H)
  H LL
• A The BRITISH amplifier produces CLEAN
  treble.
• H L(L)
  LH LH

33
Summary

• Assigns contextually based intonation
• Uses given/new information status
• Extended to fine-grained contrastive status
• Identifies contrast based on
• Knowledge base if available
• WordNet Lexical DB for greater generality

34
Conclusions

• Theme/Rheme identification difficult
• Contrast/Similarity measures for WordNet
• Still oversimplified
• Evaluation How do you tell if its right?
• Many alternatives
• Incorporate in larger discourse structure
• Discourse segments, plans, .

35
Examples

• The X4 is a SOLID-state AMPLIFIER
• LHL- H H L- L
• The X5 is a TUBE amplifier.
• LHL- H L-L
• It COSTS EIGHT HUNDRED DOLLARS,
• H H H H
  L-H
• IT costs NINE hundred dollars,
• LHL- H L-H