CS 6961: Structured Prediction Spring 2017 Practical concerns in predicting structures 1
Sofar…
• Whatarestructures?– Agraph– Acollectionofpartsthatarelabeledjointly– Acollectionofinterconnecteddecisions
• Conditionalmodels– Wewanttoconvertsomeinputtoanoutput– Modeltheconditionaldistributionoftheoutput– Scoregroupsofinter-connectedvariables
• Algorithmsforlearning– Localvs.globallearning– Differentalgorithms
• Inferencealgorithms– Predictingthefinaloutput– Differentalgorithms,tradeoffs
2
Usingthetools:Practicalconcerns
• Whatarestructures?– Agraph– Acollectionofpartsthatarelabeledjointly– Acollectionofinterconnecteddecisions
• Conditionalmodels– Wewanttoconvertsomeinputtoanoutput– Modeltheconditionaldistributionoftheoutput– Scoregroupsofinter-connectedvariables
• Algorithmsforlearning– Localvs.globallearning– Differentalgorithms
• Inferencealgorithms– Predictingthefinaloutput– Differentalgorithms,tradeoffs
3
Thislecture:
• Wewanttosolveatask.• Fornow,fullysupervised• Manychoicesahead!
Whatisthegraph?
Thebestwaytolearn?
• Modelingourproblem?• Identifyingvariables?• Identifyinggroupsthatare
scoredtogether?(factors)• Whatarefeatures?
Whatinferencealgorithm?
DoingeverythinginprogramminglanguageX
Modelingyourproblem
• Understandtheproblem:Whatshouldyourprogramproduce?– Istheredata?Veryoften,theanswerisno.L
• Whatarethedecisions/randomvariablesthatconstitutetheoutput?
• Howdotheyinteract?Identifyingfactors/parts– Someinteractionsarenatural,somearespurious(specifictoyoursmallcollectionofdata)– Someinteractionsmakeinferenceimpossibleforcomputationalreasons– Whatarethefeaturerepresentations?
• Learning– Shouldeveryscoringfunctionbejointlylearned?– Perhaps,learnsub-sectionsindependentlyandputthemtogetherwithinferenceattheend– Whichlearningalgorithm?
• Inference– Whatalgorithm?Howexpensiveisit?– Exactorapproximate?
4
Example0:NamedEntityRecognition
Goal:Toidentifypersons,locationsandorganizationsintext
B-org O B-per I-per O O
Facebook CEOMarkZuckerberg announcednewO O O O O O B-loc I-loc
privacy featuresintheconferenceinSanFrancisco
5
ObservationsStates
B-org=StartoforganizationB-per=StartofpersonI-per=Inperson
B-loc =StartoflocationI-loc =InlocationO=Notanamedentity
Example0:NamedEntityRecognition
Goal:Toidentifypersons,locationsandorganizationsintext
B-org O B-per I-per O O
Facebook CEOMarkZuckerberg announcednewO O O O O O B-loc I-loc
privacy featuresintheconferenceinSanFrancisco
6
ObservationsStates
Let’sdiscussthechoiceswehave:1. Whatarethesetofdecisionsthepredictorneedstomake?2. Howdothesedecisionsinteract?Factors?3. Features?4. Learning?Inference?
Example1:Detectingobjectsandparts
7[Farhadi,etal]
Let’sdiscussthechoiceswehave:1. Whatarethesetofdecisionsthepredictorneedstomake?2. Howdothesedecisionsinteract?Factors?3. Features?4. Learning?Inference?
Example2:Informationextraction
PhilaeisaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilitsdesignatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelanderachievedthefirst-evercontrolledtouchdownonacometnucleus.Itsinstrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.PhilaeistrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
8
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
9
Howdowemodelthisproblem?
TouchdownLander PhilaeDestination Comet 67PWhen? 12November2014
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
10
Philae
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
11
Philae Comet 67P
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
12
Philae Comet 67P
Touchdown
12 November 2014
Lander Dest. When
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
13
Howdowemodelthisproblem?
Philae Comet 67P
Touchdown
12 November 2014
Lander Dest. When
Example2:Informationextraction
Philae isaroboticEuropeanSpaceAgencylanderthataccompaniedtheRosettaspacecraftuntilits designatedlandingonComet67P/Churyumov–Gerasimenko (67P),morethantenyearsafterdepartingEarth.On12November2014,thelander achievedthefirst-evercontrolledtouchdownonacometnucleus.Its instrumentsareexpectedtoobtainthefirstimagesfromacomet'ssurfaceandmakethefirstinsituanalysistodetermineitscomposition.Philae istrackedandoperatedfromtheEuropeanSpaceOperationsCentre(ESOC)atDarmstadt,Germany.
14
Philae Comet 67P
Touchdown
12 November 2014
Lander Dest. When Let’sdiscussthechoiceswehave:1. Whatarethesetofdecisionsthepredictor
needstomake?2. Howdothesedecisionsinteract?Factors?3. Features?4. Learning?Inference?
Modelingyourproblem
• Understandtheproblem:Whatshouldyourprogramproduce?– Istheredata?Veryoften,theanswerisno.L
• Whatarethedecisions/randomvariablesthatconstitutetheoutput?
• Howdotheyinteract?Identifyingfactors/parts– Someinteractionsarenatural,somearespurious(specifictoyoursmallcollectionofdata)– Someinteractionsmakeinferenceimpossibleforcomputationalreasons– Whatarethefeaturerepresentations?
• Learning– Shouldeveryscoringfunctionbejointlylearned?– Perhaps,learnsub-sectionsindependentlyandputthemtogetherwithinferenceattheend– Whichlearningalgorithm?
• Inference– Whatalgorithm?Howexpensiveisit?– Exactorapproximate?
15