Building Text Meaning Representations from Contextually Related Frames – A Case Study – Aljoscha Burchardt Anette Frank Manfred Pinkal Saarland University.

Slides:



Advertisements
Similar presentations
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
Advertisements

CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
COGEX at the Second RTE Marta Tatu, Brandon Iles, John Slavick, Adrian Novischi, Dan Moldovan Language Computer Corporation April 10 th, 2006.
Proceedings of the Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2007) Learning for Semantic Parsing Advisor: Hsin-His.
FATE: a FrameNet Annotated corpus for Textual Entailment Marco Pennacchiotti, Aljoscha Burchardt Computerlinguistik Saarland University, Germany LREC 2008,
The SALSA experience: semantic role annotation Katrin Erk University of Texas at Austin.
Processing of large document collections Part 6 (Text summarization: discourse- based approaches) Helena Ahonen-Myka Spring 2006.
A Database of Nate Chambers and Dan Jurafsky Stanford University Narrative Schemas.
Interlingua-based MT Interlingua-based Machine Translation Syntactic transfer-based MT – Couples the syntax of the two languages What if we abstract.
Semantic Role Labeling Abdul-Lateef Yussiff
FATE: a FrameNet Annotated corpus for Textual Entailment Marco Pennacchiotti, Aljoscha Burchardt Computerlinguistik Saarland University, Germany LREC 2008,
LING NLP 1 Introduction to Computational Linguistics Martha Palmer April 19, 2006.
Comments on Guillaume Pitel: “Using bilingual LSA for FrameNet annotation of French text from generic resources” Gerd Fliedner Computational Linguistics.
Soar Progress on NL-Soar, and Introducing XNL-Soar Deryle Lonsdale, Jamison Cooper-Leavitt, and Warren Casbeer ( and the rest of the BYU NL-Soar.
Corpus-based Induction of an LFG Syntax-Semantics Interface for Frame Semantic Processing Anette Frank, Jiří Semecký
ADL Slide 1 December 15, 2009 Evidence-Centered Design and Cisco’s Packet Tracer Simulation-Based Assessment Robert J. Mislevy Professor, Measurement &
Ontology Learning and Population from Text: Algorithms, Evaluation and Applications Chapters Presented by Sole.
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
February 2009Introduction to Semantics1 Logic, Representation and Inference Introduction to Semantics What is semantics for? Role of FOL Montague Approach.
Computational Lexical Semantics Lecture 9: Learning Narrative Frames Linguistic Institute 2005 University of Chicago.
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
Learning Narrative Schemas Nate Chambers, Dan Jurafsky Stanford University IBM Watson Research Center Visit.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Lecture 12: 22/6/1435 Natural language processing Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
PropBank, VerbNet & SemLink Edward Loper. PropBank 1M words of WSJ annotated with predicate- argument structures for verbs. –The location & type of each.
Assessing the Impact of Frame Semantics on Textual Entailment Authors: Aljoscha Burchardt, Marco Pennacchiotti, Stefan Thater, Manfred Pinkal Saarland.
The Impact of Grammar Enhancement on Semantic Resources Induction Luca Dini Giampaolo Mazzini
SALSA The Saarbrücken Lexical Semantics Annotation & Acquisition Project Aljoscha Burchardt, Katrin Erk, Anette Frank, Andrea Kowalski, Sebastian Pado,
Interpreting Dictionary Definitions Dan Tecuci May 2002.
Based on “Semi-Supervised Semantic Role Labeling via Structural Alignment” by Furstenau and Lapata, 2011 Advisors: Prof. Michael Elhadad and Mr. Avi Hayoun.
A Survey for Interspeech Xavier Anguera Information Retrieval-based Dynamic TimeWarping.
Scott Duvall, Brett South, Stéphane Meystre A Hands-on Introduction to Natural Language Processing in Healthcare Annotation as a Central Task for Development.
The Current State of FrameNet CLFNG June 26, 2006 Fillmore.
NATURAL LANGUAGE UNDERSTANDING FOR SOFT INFORMATION FUSION Stuart C. Shapiro and Daniel R. Schlegel Department of Computer Science and Engineering Center.
AQUAINT 18-Month Workshop 1 Light Semantic Processing for QA Language Technologies Institute, Carnegie Mellon B. Van Durme, Y. Huang, A. Kupsc and E. Nyberg.
Modelling Human Thematic Fit Judgments IGK Colloquium 3/2/2005 Ulrike Padó.
1 Two Applications of Information Extraction to Biological Science Journal Articles: Enzyme Interactions and Protein Structures Kevin Humphreys, George.
The interface between model-theoretic and corpus-based semantics
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Using Meta-Model-Driven Views to Address Scalability in i* Models Jane You Department of Computer Science University of Toronto.
Minimally Supervised Event Causality Identification Quang Do, Yee Seng, and Dan Roth University of Illinois at Urbana-Champaign 1 EMNLP-2011.
The Unit Graphs Framework: A graph-based Knowledge Representation Formalism designed for the Meaning-Text Theory & Application to Lexicographic Definitions.
GermaNet-WS II A WordNet “Detour” to FrameNet Aljoscha Burchardt Katrin Erk Anette Frank* Saarland University, DFKI* Saarbrücken
START OF COURT PROCEEDINGS. CRIMINAL PROCEEDINGS, OFFENCES AND BAIL  Criminal proceedings start because of an arrest, summons, charge or warrant – the.
Towards Linguistically Grounded Ontologies Paul Buitelaar, Philipp Cimiano, Peter Haase, and Michael Sintek Proceedings of the 6 th European Semantic Web.
Knowledge Representation
Supertagging CMSC Natural Language Processing January 31, 2006.
Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent.
FILTERED RANKING FOR BOOTSTRAPPING IN EVENT EXTRACTION Shasha Liao Ralph York University.
NLP. Introduction to NLP Last week, Min broke the window with a hammer. The window was broken with a hammer by Min last week With a hammer, Min broke.
Knowledge Structure Vijay Meena ( ) Gaurav Meena ( )
SALSA-WS 09/05 Approximating Textual Entailment with LFG and FrameNet Frames Aljoscha Burchardt, Anette Frank Computational Linguistics Department Saarland.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
APPEALS Appeal against conviction Appeal against sentence Generally only by the defendant if he/she is found guilty (but the Prosecution can appeal a Not.
Definition and Technologies Knowledge Representation.
ALL (E GRADE): Will be able to state what the law is MOST (C GRADE): Will be able to explain at least 2 of the prompts SOME (A GRADE): Will be able to.
A Database of Narrative Schemas A 2010 paper by Nathaniel Chambers and Dan Jurafsky Presentation by Julia Kelly.
Comparing the Inquisitorial and Adversarial Systems.
Relation Extraction (RE) via Supervised Classification See: Jurafsky & Martin SLP book, Chapter 22 Exploring Various Knowledge in Relation Extraction.
Outline of the U.S. and Arizona Criminal Justice Systems
Learning Attributes and Relations
Statistical NLP: Lecture 3
INAGO Project Automatic Knowledge Base Generation from Text for Interactive Question Answering.
Two Discourse Driven Language Models for Semantics
The Criminal Justice Process
CSC 594 Topics in AI – Applied Natural Language Processing
Lecture 9: Semantic Parsing
Nov. 29, 2001 Ontology Based Recognition of Complex Objects --- Problems to be Solved Develop Base Object Recognition algorithms that identify non-decomposable.
Unsupervised Learning of Narrative Schemas and their Participants
Presentation transcript:

Building Text Meaning Representations from Contextually Related Frames – A Case Study – Aljoscha Burchardt Anette Frank Manfred Pinkal Saarland University and DFKI Saarbrücken

Motivation  Broad-coverage statistical parsing systems –High demand for more „semantics-based“ processing  Deep computational semantic processing –Well-studied formalisms for truth-conditional and discourse semantics –Large-scale deep semantic parsing (e.g., Bos et al., 2004) –Little emphasis on lexical semantics and concept-based analysis  Lexical semantic resources –WordNet(s) used for approximate concept-based analysis –Lexical semantics resources that model predicate-argument structure (e.g. FrameNet, PropBank) –Automatic semantic role labelling (ConLL, Senseval)  Aim: Building partial text meaning representations from frame-annotated deep syntactic structures

Overview Frame Semantics for Partial Text Meaning Representation  Background: FrameNet „as a Net“  Building text meaning representations from frame semantic annotations A case study Linking of contextually related frames and frame roles –Based on patterns of lexico-semantic and contextual relations Generalisation and acquisition of linking patterns  Towards Automation: current architecture  Conclusion

FrameNet  Frame Semantics (Fillmore 1976, 1977,..) –Frame: a conceptual structure or prototypical situation –Frame elements (roles) Identify participants of the situation Are local to their frame –Frame evoking elements (verbs, nouns, adjectives) introduce frames –E.g. VERDICT: [The jury] Judge convicted [him] Defentant [on the counts of theft] Charges. On Thursday [a jury] Judge found [the youth] Defendant [guilty of wounding Mr Lay] Finding  Berkeley FrameNet Project –Database of frames for core lexicon of English –Current release: 610 frames, about 9000 lexical units

FrameNet „as a Net“ – Frame-to-Frame Relations – Inheritance relation: a frame inherits all roles of one or more “super” frame(s) PatientAgent ChargesOffense AuthoritiesSuspect Intentionally_act Arrest

FrameNet „as a Net“ – Frame-to-Frame Relations – Subframe relation –Super frame represents complex event –Subframes represent sub-events –Subframes usually inherit some roles of the super frame Criminal process ArraignmentArrestSentencingTrial Charge Judge Defendant Defense Court Jury Offense Prosecution Charge Defendant...

Frame Semantics for Partial Text Meaning Representation  Probabilistic models for semantic role labeling (Gildea & Jurafsky, 2002)  Frame semantic projection from deep (LFG) grammar (Frank & Erk, 2003) –No constructional “glue” –Partially connected/embedded lexico-semantic predicate- argument structures –Coarse-grained semantic structures  Challenge: obtain a more densely connected representation –By learning and applying heuristic linking patterns

A Case Study In the first trial in the world in connection with the terrorist attacks of 11 September 2001, the Higher Regional Court of Hamburg has passed down the maximum sentence. Mounir al Motassadeq will spend 15 years in prison. The 28-year-old Moroccan was found guilty as an accessory to murder in more than 3000 cases.

Local Roles In the first trial in the world in connection with [the [terrorist] Assailant attacks of [11 September 2001] Time ] Case, [the Higher Regional Court of Hamburg] Court has passed down the [maximum] Type sentence.

Local Roles [Mounir al Motassadeq] Inmates will spend [15 years] Duration in prison.

Local Roles [The 28-year-old Moroccan] Defendant was found [guilty] Finding as [an accessory to [murder] FocalEntity [in more than 3000 cases] Victim ] Charge.

Unfilled Roles TargetFrameFrame rolesFiller (given vs. Induced) trial TRIAL CASE terrorist attacks(1) CHARGE accessory to murder(2) COURT Higher Regional Court (3) DEFENDANT...28-year-old Moroccan(4) attacks ATTACK ASSAILANT terrorist(5) VICTIM...(6) TIME (exth.)11 September 2001(7) sentence SENTENCING CONVICT Mounir al Motassadeq(8) COURT Higher Regional Court(9) TYPE...maximum sentence(10) prison PRISON INMATES...Mounir al Motassadeq(11) DURATION (exth.) 15 years(12) found VERDICT CASE terrorist attacks(13) CHARGE accessory to murder(14) DEFENDANT 28-year-old Moroccan(15) FINDING...guilty(16) accessoryASSISTANCE CO-AGENT (17) FOCAL_ENTITY murder(18) HELPER...28-year-old Moroccan(19) murder KILLING KILLER (20) VICTIM...m.t cases(21)

Frames in Context TargetFrameFrame rolesFiller (given vs. Induced) trial TRIAL CASE terrorist attacks(1) CHARGE accessory to murder(2) COURT Higher Regional Court (3) DEFENDANT...28-year-old Moroccan(4) attacks ATTACK ASSAILANT terrorist(5) VICTIM...(6) TIME (exth.)11 September 2001(7) sentence SENTENCING CONVICT Mounir al Motassadeq(8) COURT Higher Regional Court(9) TYPE...maximum sentence(10) prison PRISON INMATES...Mounir al Motassadeq(11) DURATION (exth.) 15 years(12) found VERDICT CASE terrorist attacks(13) CHARGE accessory to murder(14) DEFENDANT 28-year-old Moroccan(15) FINDING...guilty(16) accessoryASSISTANCE CO-AGENT (17) FOCAL_ENTITY murder(18) HELPER...28-year-old Moroccan(19) murder KILLING KILLER (20) VICTIM...m.t cases(21)

Frames in Context TargetFrameFrame rolesFiller (given vs. Induced) trial TRIAL CASE terrorist attacks(1) CHARGE accessory to murder(2) COURT Higher Regional Court (3) DEFENDANT...28-year-old Moroccan(4) attacks ATTACK ASSAILANT terrorist(5) VICTIM...(6) TIME (exth.)11 September 2001(7) sentence SENTENCING CONVICT Mounir al Motassadeq(8) COURT Higher Regional Court(9) TYPE...maximum sentence(10) prison PRISON INMATES...Mounir al Motassadeq(11) DURATION (exth.) 15 years(12) found VERDICT CASE terrorist attacks(13) CHARGE accessory to murder(14) DEFENDANT 28-year-old Moroccan(15) FINDING...guilty(16) accessoryASSISTANCE CO-AGENT (17) FOCAL_ENTITY murder(18) HELPER...28-year-old Moroccan(19) murder KILLING KILLER (20) VICTIM...m.t cases(21)

Linking Frames and Roles in Context  At the instance level –given frame instances f 1 :F 1 and f 2 :F 2, where f 1 and f 2 stand in a contextual relation (syn, sem, discourse) frame types F 1 and F 2 stand in some frame relation => identify role instances (referents) of f 1 and f 2 (r 1 (= r 0 ) = r 2 ) frame relation context-related instances inferred relation

Linking Frames and Roles in Context In the first trial in the world in connection with the terrorist attacks of 11 September 2001, the Higher Regional Court of Hamburg has passed down the maximum sentence. Criminal Process Trial Sentencing Court frame relation

Linking Frames and Roles in Context In the first trial (f 1 ) in the world in connection with the terrorist attacks of 11 September 2001, [the Higher Regional Court of Hamburg] (r 2 ) has passed down the maximum sentence (f 2 ). The Higher Regional Court of Hamburg Functional Embedding Criminal Process Trial Sentencing Court frame relation context-related instances

Linking Frames and Roles in Context The Higher Regional Court of Hamburg Functional Embedding Criminal Process Trial Sentencing Court frame relationcontext-related instancesinferred relation In the first trial (f 1 ) in the world in connection with the terrorist attacks of 11 September 2001, [the Higher Regional Court of Hamburg] (r 2 =r 0 = r 1 ) has passed down the maximum sentence (f 2 ).

Linking Frames and Roles in Context  At the type level (more involved) –If instances of frame roles f 1 :F 1 and f 2 :F 2 are often found co- referent within particular contextual relations => Hypothesize a frame relation between F 1 and F 2 (no) frame relation context-related instances inferred relation

Linking Frames and Roles in Context (no) frame relation context-related instances inferred relations … the Higher Regional Court of Hamburg has passed down the Maximum sentence. [Mounir al Motassadeq] will spend 15 years in prison. Sentencing Prison Convict Inmates Discourse Relation New Frame Relation (Role Binding: Convict=Inmates) (Co-reference)

Meaning Postulates („Semantic Control“)  Example: the Defendant in a VERDICT is the actor of the Frame embedded in the VERDICT Charge role („Charge event“)  Modeled as „Semantic Control“: –VERDICT embeds some frame Fx under role Charge, –Fx.Rx inherits from INTENT._ACT.AGENT => VERDICT.Defendant equals Fx.Rx (at the type level) VERDICT Fx INTENT._ ACT Agent Rx Charge Defendant Semantic Control „[...Moroccan] DEF was found guilty as an accessory (Fx) to murder“ => VERDICT.Defendant equals ASSISTANCE.Helper

Generalisation  Selected deeper semantic represention to model –referential properties (introduction of new discourse referents) => blocking factors for role identification rules –Temporal sequence and locational properties => deeper contextual semantic relations between frames Mounir El Motassadeq (born April 3, 1974) is a Moroccan. In February 2003 he was convicted [...]. As of April 2004 he is the only person to have been convicted in direct relation to the September 11, 2001 attacks. The verdict and sentence were set aside on appeal [...]. A new trial is expected in mid-2004.

Acquisition of Linking Patterns  Identified patterns for induction of role-linking –Lexico-semantic relations Subframe and Inheritance relation, Semantic Control –Contextual relations Syntactic and semantic embedding Anaphoricity and referential properties Discourse relations (or surface linearisation)  Future work –Learning weighted role-linking patterns from annotated texts in restricted domains, to be used as probabilistic inference rules –“[Baragiola] CONVICT / ESCAPEE had previously been convicted of murder in Italy, but had escaped in 1980 and obtained Swiss citizenship.” => Infer PRISON and PRISON.Inmates = ESCAPE.Escapee

Current Architecture  LFG-based parsing and syntax-semantics interface –ParGram grammars for German and English (Butt et al. 2002) –Frame projection from f-structure (XLE transfer system) –Interfaces to statistical frame assignment (Baldewein et al. 2004)  Enriching Semantic Representation –Rule-based refinement of semantic representation –Autom. assignment of SUMO/MILO classes (using WordNet WSD)  Logical Representation and Reasoning –Frame relations translated to logic programs –Joint work with P. Baumgartner and F. Suchanek, MPI Saarbrücken –First scenario: RTE Challenge

Conclusion  Combining –Deep syntactic analysis and Frame Semantic role assignments  Methods –Linking partial frame annotations in context –Generalisation and automation  Shallow semantic representations –Necessarily partial (focusing on open class categories) –Robust semantic processing for coarse-grained information access –Incremental depth for finer-grained analysis

Frame Exchange Format „fef“

Types of Relations  FrameNet Relations –Frame hierarchy: inherits –Subframes  Contextual Relations between instantiated frames and roles –Syntactic and/or semantic embedding –Discourse relations –Anaphoric relations  Inferences –On the basis of both

CRIMINAL PROCESS SENTENCING (1)TRIAL (1) VERDICT (3) Defendant KILLING (3) Inferred Relation Contextual Relation Killer Subframe/FE PRISON (2) InmatesDuration ASSISTANCE (3) HelperCo_agentFocal_entityVictim ConvictType Court CaseCharge CaseCharge Court Finding (1)sentence number Frame, Contextual, and Inferred Relations

CRIMINAL PROCESS SENTENCINGTRIAL VERDICT Defendant (the Moroccan) KILLING Inference Contextual Relations Killer Hierarchy/Subframe/FE PRISON Inmates (Motus.) Duration (15Y) ASSISTANCE HelperCo_agentGoal (murder) Victim (3000) ConvictDuration (maximum) Court (Hmbg.) Case (9/11) Charge CaseCharge (accessory) In the first trial.. the higher Regional Court.. has passed down the maximum sentence. Mounir al Motussadeq will spend 15 years in prison. The 28-year-old Moroccan was found guilty as an accessory to murder in cases.

More Involved Examples Semantic control A meaning relation between frame roles F2:R2 and Fx:Rx –where F2 embeds Fx (via some role R3), and –F2:R2 semantically controls (is co-referent with) the AGENT role Fx:Rx of Fx frame relation context-related instances inferred relation

More Involved Examples Semantic control Example: „... was found guilty as an accessory to murder“ VERDICT foundCASE terrorist attacks(13) CHARGE accessory to murder(14) DEFENDANT 28-year-old Moroccan(15) FINDING...guilty(16) INTENTIONALLY_ACTAGENT ASSISTANCE accessoryCO-AGENT (17) FOCAL_ENTITY murder(18) HELPER...28-year-old Moroccan(19) frame relation context-related instances inferred relation

More Involved Examples (?)  Semantic Control – „... was found guilty as an accessory to murder“ The CO-AGENT of ASSISTANCE is co-referent with the AGENT of the frame embedded under ASSISTANCE.FOCAL_ENTITY => ASSISTANCE.CO-AGENT coreferent with KILLING.KILLER –SENTENCING.CONVICT co-referent with PRISON.INMATES CAUSATION.CAUSE embeds SENTENCING CAUSATION.EFFECT embeds PRISON PATIENT(CAUSATION.CAUSE) co-referent with PATIENT(CAUSATION.EFFECT) (semantic control) (where PATIENT(Frame) inherits from INTENTIONALLY_AFFECT.PATIENT) PATIENT(SENTENCING) = SENTENCING.CONVICT => PATIENT(PRISON) = PRISON.INMATES