Building Text Meaning Representations from Contextually Related Frames – A Case Study – Aljoscha Burchardt Anette Frank Manfred Pinkal Saarland University and DFKI Saarbrücken
Mar 21, 2016
Building Text Meaning Representations from Contextually Related Frames
– A Case Study –
Aljoscha BurchardtAnette Frank
Manfred PinkalSaarland 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
Authorities Suspect
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
Criminalprocess
Arraignment Arrest Sentencing Trial
Charge
JudgeDefendant
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
Target Frame Frame roles Filler (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)
accessory ASSISTANCE CO-AGENT (17)FOCAL_ENTITY murder (18)HELPER ... 28-year-old Moroccan (19)
murder KILLING KILLER (20)VICTIM ... m.t. 3000 cases (21)
Frames in Context
Target Frame Frame roles Filler (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)
accessory ASSISTANCE CO-AGENT (17)FOCAL_ENTITY murder (18)HELPER ... 28-year-old Moroccan (19)
murder KILLING KILLER (20)VICTIM ... m.t. 3000 cases (21)
Frames in Context
Target Frame Frame roles Filler (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)
accessory ASSISTANCE CO-AGENT (17)FOCAL_ENTITY murder (18)HELPER ... 28-year-old Moroccan (19)
murder KILLING KILLER (20)VICTIM ... m.t. 3000 cases (21)
Linking Frames and Roles in Context
At the instance level– given frame instances f1:F1 and f2:F2, where
• f1 and f2 stand in a contextual relation (syn, sem, discourse)
• frame types F1 and F2 stand in some frame relation
=> identify role instances (referents) of f1 and f2 (r1 (= r0) = r2)
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
SentencingCourt
frame relation
Linking Frames and Roles in Context
In the first trial (f1) in the world in connection with the terrorist attacks of 11 September 2001, [the Higher Regional Court of Hamburg] (r2) has passed down the maximum sentence (f2).
The Higher Regional Court of Hamburg
Functional Embedding
Criminal Process
Trial
SentencingCourt
frame relation context-related instances
Linking Frames and Roles in Context
The Higher Regional Court of Hamburg
Functional Embedding
Criminal Process
Trial
SentencingCourt
frame relation context-related instances inferred relation
In the first trial (f1) in the world in connection with the terrorist attacks of 11 September 2001, [the Higher Regional Court of Hamburg] (r2=r0= r1) has passed down the maximum sentence (f2).
Linking Frames and Roles in Context
At the type level (more involved)– If instances of frame roles f1:F1 and f2:F2 are often found co-
referent within particular contextual relations=> Hypothesize a frame relation between F1 and F2
(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
ChargeDefendant
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 2004he is the only person to have been convicted in direct relationto the September 11, 2001 attacks. The verdict and sentencewere set aside on appeal [...]. A new trial is expectedin 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
Defendant
KILLING (3)
Inferred RelationContextual Relation Killer
Subframe/FE
PRISON (2)
Inmates Duration
ASSISTANCE (3)
Helper Co_agentFocal_entityVictim
Convict Type Court CaseCharge
CaseCharge
Court
Finding
(1) sentence number
Frame, Contextual, and Inferred Relations
CRIMINAL PROCESS
SENTENCING TRIAL
VERDICT
Defendant
Defendant(the Moroccan)
KILLINGInferenceContextual Relations
Killer
Hierarchy/Subframe/FE
PRISON
Inmates(Motus.)
Duration(15Y)
ASSISTANCE
Helper Co_agentGoal(murder)
Victim(3000)
Convict Duration(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 .. 3000 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 found CASE terrorist attacks (13) CHARGE accessory to murder (14)
DEFENDANT 28-year-old Moroccan (15)FINDING ... guilty (16)
INTENTIONALLY_ACT AGENT
ASSISTANCE accessory CO-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 PRISONPATIENT(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