Parsing and Analysis for SpeechtoSpeech MT

1
Parsing and Analysisfor Speech-to-Speech MT

• Discussion Leader Alon Lavie
• Carnegie Mellon University

2
Main Issues

• Target Representation
• Robustness Issues
• Speech disfluencies and spontaneity
• Dealing with output from Speech Recognizers
• Portability and Adaptation Issues
• Domain portability
• Language portability
• Language diversity Issues

3
What is the Target Representation?

• Different MT approaches require different
  analysis representations
• Interlingua deep and detailed vs. shallow
• Transfer approaches syntactic representation
• Some MT approaches dont require real parsing
  at all
• Statistical MT
• Example-based MT

4
Robustness Issues

• Speech disfluencies and spontaneity
• Spoken language is very different than written
  text short turns, back-channels, looser notion
  of grammar, fixed expressions/constructions,
  elided words and constituents
• (wanna go eat? gt Do you want to go to eat?)
• Disfluencies are common
• Filled pauses uh, um, you know
• False starts and repairs I got to I think I
  have to be there at
• Dealing with output of Speech Recognizers
• High word error rates
• Lack of punctuation and sentence boundaries

5
Robustness Issues

• How do we build parsers/analyzers that can deal
  with such language?
• Focus more on semantics rather than syntax
• Focus on language properties of the domain (fixed
  expressions, task oriented language)
• Clean-up the language
• Detect and remove disfluencies
• Detect SDUs (semantic dialogue units)
• Use prosodic information pauses, intonation

6
Portability Issues

• Can we develop parsing/analysis methods that can
  be rapidly adapted to new languages and new
  domains?
• Some trends
• Focus on machine learning and trainable
  approaches data-driven MT approaches, grammar
  induction, transfer-rule learning
• Multi-engine systems that can adapt to the
  resources that are available

7
Language Diversity Issues

• Different languages have very different
  characteristics - how do we deal with the
  diversity of phenomena?
• Morphologically synthetic to analytic
• word order free to fixed
• diverse dialects within languages
• Some approaches more portable in nature, less
  sensitive to these differences
• Related to language and domain portability

8
Example CMUs JANUS

• Target Representation shallow task-oriented
  interlingua representation
• I would like to take a vacation in
  val-di-fiemme" 
• cgive-informationdispositiontrip
• (disposition(whoi, desire),
• visit-spec(identifiabilityno,vacation),
  
• location(place-nameval_di_fiemme))
• Hybrid Statistical/Rule-based analysis approach
• Semantic phrases are parsed using a robust parser
• Trainable classifier used for selection of domain
  action

9
Example CMUs MilliRADD Rapidly Adaptable Data
Driven MT With Limited Resources
EBMT
The reporter interviewed the ambassador in
America.
?????? ?????
Multi-Engine Integration
SMT
iRBMT
NBNB PP DE" NB -gt NB PP ((X3Y1)
Alignments (X1Y2) ((X0 ppadj) X1) X-side
constraints (X0 X3) (Y0 X0) Transfer
constraints (x2 (x0 ppadj)) Generation
constraints (x1 x0)) PPPP ZAI" NP PREP
-gt PREP NP ((X3Y1) Alignments (X2Y2)
((X3 loc) c ) X-side constraints ((X0 obj)
X2) (X0 X3) (Y0 X0) Transfer constraints
(X2 (x0 obj)) Generation constraints (x1
x0))
Automatic Learning of Xfer Rules
10
Example Parsing the CHILDES Database

• Goal syntactic annotation of transcribed
  conversations of children and their parents
• Target Representation complete syntactic
  feature-structures
• MOT you kicked it . 
• mor proyou vkick-PAST proit .
• fst ((mood declarative) (tense past) (index
  2)
• (subject ((cat pro) (num sg) (pers 2) (case
  nom)
• (index 1) (root you)))
• (object ((cat pro) (sum sg) (pers 3) (case
  acc)
• (index 3) (root it)))
• (root kick) (cat v))
•  
• cst (sentence (decl (np (pro you))
• (vp (vbar (v kicked)
• (np (pro it)))))
• (period .))
• Analysis Approach multi-pass robust parser
  (LCFlex) that gradually relaxes constraints
• Sagae, Lavie MacWhinney, IWPT-01

11
Discussion Topics

• Sharing of available data resources and
  components
• Robust parsers
• Annotated data and bilingual corpora
• Coding schemes interlingua, other,

12
Discussion Topics

• Approaches to Parsing/Analysis
• Focus on specific approaches or support a wide
  variety of different approaches?
• Common target representations?
• Example the C-STAR model common interlingua
  representation, but independent analysis
  approaches
• Multi-Engine systems how do we put together an
  effective combined system?
• Models of collaboration

13
Discussion Topics

• Language and Domain Portability
• How do we encourage approaches that are more
  suited for fast adaptation to new languages and
  domains?