1 / 27

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

Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing. Anette Frank, Ji ří Semecký frank@coli.uni-sb.de semecky@ ufal.ms.mff.cuni.cz. Overview State of the art Our work Conclusion. Overview. State of the art Frame Semantics and FrameNet project

kesler
Télécharger la présentation

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

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Corpus-based Inductionof an LFG Syntax-Semantics Interfacefor Frame Semantic Processing Anette Frank, Jiří Semecký frank@coli.uni-sb.de semecky@ufal.ms.mff.cuni.cz

  2. 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

  3. 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

  4. 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

  5. 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

  6. 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

  7. 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

  8. 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

  9. 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

  10. 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

  11. 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

  12. 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

  13. 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

  14. 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

  15. 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

  16. 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

  17. 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

  18. 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

  19. 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

  20. 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

  21. 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

  22. 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

  23. 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

  24. 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

  25. 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

  26. 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

  27. 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

More Related