corpus based induction of an lfg syntax semantics interface for frame semantic processing
Download
Skip this Video
Download Presentation
Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing

Loading in 2 Seconds...

play fullscreen
1 / 27

Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing - PowerPoint PPT Presentation


  • 84 Views
  • Uploaded on

Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing. Anette Frank, Ji ří Semecký [email protected] [email protected] ufal.ms.mff.cuni.cz. Overview State of the art Our work Conclusion. Overview. State of the art Frame Semantics and FrameNet project

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

PowerPoint Slideshow about ' Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing' - kesler


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
corpus based induction of an lfg syntax semantics interface for frame semantic processing

Corpus-based Inductionof an LFG Syntax-Semantics Interfacefor Frame Semantic Processing

Anette Frank, Jiří Semecký

[email protected]

[email protected]

overview

Overview

State of the art

Our work

Conclusion

Overview
  • State of the art
    • Frame Semantics and FrameNet project
    • Salsa frame annotation project
    • LFG syntax-semantics interface for Frame Semantics
  • Our work
    • Porting SALSA frame annotations to LFG
    • Special phenomena
    • Extraction of frame assignment rules
  • Conclusion
    • Current data and results
    • Summary
    • Next steps [and Application]

LFG 2004, Christchurch

frame semantics

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

Frame Semantics
  • Frame Semantics (Fillmore 1976, 1977, ..)
    • Frame: a conceptual structure or prototypical situation,

e.g. SPD requests that coalition talk about reform.

    • Evokes a frame REQUEST,with frame elements (frame semantic roles) that identify participants
      • SPEAKER, SPD
      • ADDRESSEE, Coalition
      • MESSAGE, talk about reform
    • Frame evoking elements: verbs, nouns, adjectives, ... introduce frames
  • FrameNet
    • Berkeley FrameNet II Project
    • Database of frames for a lexicon of English
      • Definition of frames and frame semantic roles
      • Inheritance relations among frames
      • Selected and manually annotated example sentence

LFG 2004, Christchurch

salsa saarbr cken lexical semantics annotation and analysis project

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

SALSA Saarbrücken Lexical Semantics Annotation and Analysis Project
  • German FrameNet “light”
    • Creating a large semantically annotated corpus of German
    • Building on FrameNet DB definitions of frames and roles
    • Strongly corpus-based oriented
  • Methods and Aims
    • Manual annotation on top of syntactically annotated TIGER corpus
    • (Semi-)automatic semantic annotation of larger corpora
    • Automatic acquisition of a lexical semantic resource
    • Semantics-based information access in NLP applications
  • Focus of our work
    • Induction of an LFG syntax-semantics interface for frame semantics from manually annotated corpus

LFG 2004, Christchurch

salsa example

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

SALSAExample
  • TIGER
    • Newspaper corpus
    • 1.5 Million words
  • TIGER annotation scheme
    • Syntactic constituents
    • Functional role labels (SB, HD, ..)
    • Crossing edges (word order)

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

salsa example1

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

SALSAExample
  • TIGER
    • Newspaper corpus
    • 1.5 Million words
  • TIGER annotation scheme
    • Syntactic constituents
    • Functional role labels (SB, HD, ..)
    • Crossing edges (word order)
  • SALSA frame annotation
    • Frame evoking element, FEE,(fordert auf) projects frame

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

salsa example2

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

SALSAExample
  • TIGER
    • Newspaper corpus
    • 1.5 Million words
  • TIGER annotation scheme
    • Syntactic constituents
    • Functional role labels (SB, HD, ..)
    • Crossing edges (word order)
  • SALSA frame annotation
    • Frame evoking element, FEE,(fordert auf) projects frame
    • Frame elements (FEs) of the frame are connectedto syntactic constituents

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

salsa example3

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

SALSAExample
  • TIGER
    • Newspaper corpus
    • 1.5 Million words
  • TIGER annotation scheme
    • Syntactic constituents
    • Functional role labels (SB, HD, ..)
    • Crossing edges (word order)
  • SALSA frame annotation
    • Frame evoking element, FEE,(fordert auf) projects frame
    • Frame elements (FEs) of the frame are connectedto syntactic constituents

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

from salsa to lfg

Overview

State of the art

Our work

Conclusion

Frame Semantics

Salsa

From SALSA to LFG

From SALSA to LFG
  • Automatic semantic frame assignment
    • Broad-coverage grammar
    • High accuracy
    • Portability of manual SALSA/TIGER frame annotations
  • German LFG grammar (IMS, Univ. Stuttgart)
    • Used for TIGER annotation: 50% coverage, 70% precision
    • Further extension of coverage
    • OT-based and statistical disambiguation
  • A general syntax-semantics interface
    • LFG f-structures provide a good level of abstraction
    • PARGRAM: Common f-structure design principles for different languages allow study of generalizations across languages

LFG 2004, Christchurch

an lfg frame semantics projection

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

An LFG Frame Semantics Projection
  • Projection from f-structure

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

an lfg frame semantics projection1

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

An LFG Frame Semantics Projection
  • Projection from f-structure

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

an lfg frame semantics projection2

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

An LFG Frame Semantics Projection
  • Projection from f-structure

SPD fordert Koalition zu Gespräch über Reform auf.

SPD requests that coalition talk about reform.

LFG 2004, Christchurch

an lfg frame semantics projection3

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

An LFG Frame Semantics Projection

auffordern V,

(PRED) = ‘AUFFORDERN <(SUBJ) (OBJ) (OBL OBJ)>’

...

( () FRAME) = REQUEST

( () FEE) = ( PRED FN)

( () SPEAKER) =  ( SUBJ)

( () ADDRESSEE) =  ( OBJ)

( () MESSAGE) =  ( OBL OBJ)

  • Co-description:lexicon entry for frame projection

pred (X, auffordern),

subj (X, A), obj (X, B), obl (X, C), obj (C, D)

==>

+ (X, SemX), +frame (SemX, request), +fee (SemX, auffordern),

+ (A, SemA), +speaker (SemX, SemA),

+ (B, SemB), +addressee (SemX, SemB),

+ (D, SemD), +message (SemX, SemD),

  • Description by Analysis:transfer rule for frame projection

LFG 2004, Christchurch

corpus based induction of frame assignment rules

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Corpus-based inductionof frame assignment rules
  • Step 1: Porting SALSA annotations to LFG
    • Using “parallel” LFG corpus of TIGER
    • To obtain an LFG-frame corpus
  • Step 2: Induction of general frame assignment rules from the LFG-frame corpus
    • Can be applied to f-structure output of LFG parsing of new sentences

LFG 2004, Christchurch

porting salsa annotations to lfg

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

501

1

2

3

8

Porting SALSA Annotations to LFG
  • Frame evoking elements (FEE) and frame elements (FE) connected to syntactic constituents identified by IDs
  • Extracting frame constituting information from SALSA/TIGER annotations
    • FRAME, TIGER constituent IDentifiers of FEE and FEs

LFG 2004, Christchurch

porting salsa annotations to lfg1

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

501

1

2

3

8

Porting SALSA Annotations to LFG
  • „Parallel“ TIGER corpus consisting of automatically derived LFG f-structures (Forst 2003)
  • Using treebank conversion methods
  • Preserves TIGER constituent information (ID)

LFG 2004, Christchurch

porting salsa annotations to lfg an lfg corpus with frame semantic projection

Overview

State of the art

Our work

Consequences

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Porting SALSA Annotations to LFG An LFG Corpus with frame Semantic Projection
  • Identify f-structure nodes of FEE and FEs, using IDs as anchor
  • Define semantic projection for frame and all the frame elements
  • Using rewrite rules of XLE transfer system

LFG 2004, Christchurch

special phenomena

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Special Phenomena
  • Multiple constituents
    • Asymmetric embedding
  • Coordination
  • Multiword expressions
  • Underspecification

LFG 2004, Christchurch

special phenomena multiword expressions

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Special PhenomenaMultiword Expressions
  • Idiomatic expression evokes frame for non-literal meaning
    • „über die Ladentheke gehen“ -- „sell“
  • Project individual components to set-valued FEE-MWE

Vier Artikel gingen über die Ladentheke.

Four items went over the counter

“Four items were sold.”

LFG 2004, Christchurch

corpus based induction of frame rules

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Corpus-based induction of frame rules
  • Step 1: Porting SALSA annotations to LFG
    • Using “parallel” LFG corpus of TIGER
    • To obtain an LFG-frame corpus
    • Rules anchored to node IDs
  • Step 2: Induction of general frame assignment rules from the LFG-frame corpus
    • Can be applied to f-structure output of LFG parsing of new sentences
    • Rules anchored to functional descriptions

FE assignment (auffordern)

(SUBJ) –SPEAKER

(OBJ) –ADDRESSEE

(OBL OBJ) –MESSAGE

LFG 2004, Christchurch

extraction of functional paths

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Extraction of Functional Paths
  • FE assignment paths
    • Paths relative to FEE
  • Local and non-local
    • Non-local = with inside out relative path
    • Prefer local to non-local

SPD verspricht Wählern, Beschüsse mitzuteilen.

SPD promises voters to report decisions.

LFG 2004, Christchurch

extraction of functional paths1

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Extraction of Functional Paths
  • Prefer local to non-local
    • SPEAKER => choose SUBJ
  • In ambiguous non-local paths choose „shortest non-local sub-path“
    • Prefer (XCOMP ) SUBJ to (XCOMP XCOMP ) SUBJ
  • Non-local paths of equal length considered equally good
    • Choose both (XCOMP ) OBJ and (ADJ ) OBJ

LFG 2004, Christchurch

applying rules to new sentences

Overview

State of the art

Our work

Conclusion

An LFG Frame Semantic Projection

Porting SALSA Annotations to LFG

Special phenomena

Extraction of Frame Assignment Rules

Applying rules to new sentences
  • mitteilen: COMMUNICATION; SUBJ  SPEAKER, OBJ  MESSAGE
  • Complete frames with all frame elements
    • As instantiated in the corpus
    • Problem: unseen configurations (sparse data problem)
  • Partial annotation
    • Individual rules for the FEE
    • Individual rules for each FE of the frame (conditioned on FEE)

LFG 2004, Christchurch

current data and results

Overview

State of the art

Our work

Conclusion

Current Data and Results

Summary

Next steps and Application

Current Data and Results
  • Data used:
    • 12127 frame assignment rules
    • 10009 sentences
  • Successfully ported frames: 11612
  • Compiled transfer rules after path extraction: 9334
  • Local vs. non-local FE assignments:87.18% vs. 12.82%
  • Ambiguity rate:
    • Average 8.83 rules per FEE
    • Average 41.27 rules per frame

LFG 2004, Christchurch

current data and results1

Overview

State of the art

Our work

Conclusion

Current Data and Results

Summary

Next steps and Application

Current Data and Results
  • Re-applying syntax-semantics mapping rules to TIGER-LFG corpus
  • Applying syntax-semantics mapping rules to free LFG parsing (without statistical disambiguation)

LFG 2004, Christchurch

summary

Overview

State of the art

Our work

Conclusion

Current Data and Results

Summary

Next steps and Application

Summary
  • Modeling frame semantics in LFG framework
  • Porting frame annotations from TIGER/SALSA to an LFG corpus
  • Extracting general frame assignment rules for LFG parsing
  • Applying frame assignment rules in an LFG parsing architecture

LFG 2004, Christchurch

next steps

Overview

State of the art

Our work

Conclusion

Current Data and Results

Summary

Next steps and Application

Next steps
  • Semantically driven syntactic disambiguation
    • Reduce ambiguity of syntactic parses
    • Prefer parses with corresponding semantic annotation
  • Stochastic modeling for semantic role assignment
    • Training stochastic models on the basis of corpus annotations
    • For disambiguation of disjunctive frame assignments
    • XLE: statistical ME package for training and online disambiguation

LFG 2004, Christchurch

ad