This two-volume set LNAI 7523 and LNAI 7524 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: ECML PKDD 2012, held in Bristol, UK, in September 2012. The 105 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 443 submissions. The final sections of the proceedings are devoted to Demo and Nectar papers. The Demo track includes 10 papers (from 19 submissions) and the Nectar track includes 4 papers (from 14 submissions). The papers grouped in topical sections on association rules and frequent patterns; Bayesian learning and graphical models; classification; dimensionality reduction, feature selection and extraction; distance-based methods and kernels; ensemble methods; graph and tree mining; large-scale, distributed and parallel mining and learning; multi-relational mining and learning; multi-task learning; natural language processing; online learning and data streams; privacy and security; rankings and recommendations; reinforcement learning and planning; rule mining and subgroup discovery; semi-supervised and transductive learning; sensor data; sequence and string mining; social network mining; spatial and geographical data mining; statistical methods and evaluation; time series and temporal data mining; and transfer learning.

This two-volume set LNAI 7523 and LNAI 7524 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: ECML PKDD 2012, held in Bristol, UK, in September 2012. The 105 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 443 submissions. The final sections of the proceedings are devoted to Demo and Nectar papers. The Demo track includes 10 papers (from 19 submissions) and the Nectar track includes 4 papers (from 14 submissions). The papers grouped in topical sections on association rules and frequent patterns; Bayesian learning and graphical models; classification; dimensionality reduction, feature selection and extraction; distance-based methods and kernels; ensemble methods; graph and tree mining; large-scale, distributed and parallel mining and learning; multi-relational mining and learning; multi-task learning; natural language processing; online learning and data streams; privacy and security; rankings and recommendations; reinforcement learning and planning; rule mining and subgroup discovery; semi-supervised and transductive learning; sensor data; sequence and string mining; social network mining; spatial and geographical data mining; statistical methods and evaluation; time series and temporal data mining; and transfer learning.

Thisvolumecontains3invitedand24submittedpaperspresentedattheNinth InternationalWorkshoponInductiveLogicProgramming, ILP-99. The24acc- tedpaperswereselectedbytheprogramcommitteefromthe40paperssubmitted toILP-99. Eachpaperwasreviewedbythreereferees, applyinghighreviewing standards. ILP-99washeldinBled, Slovenia,24{27June1999. Itwascollocatedwith theSixteenthInternationalConferenceonMachineLearning, ICML-99, held27{ 30June1999. On27June, ILP-99andICML-99weregivenajointinvitedtalk byJ. RossQuinlanandajointpostersessionwhereallthepapersacceptedat ILP-99andICML-99werepresented. TheproceedingsofICML-99(editedby IvanBratkoandSa soD zeroski)arepublishedbyMorganKaufmann. WewishtothankalltheauthorswhosubmittedtheirpaperstoILP-99, the programcommitteemembersandotherreviewersfortheirhelpinselectinga high-qualityprogram, andtheinvitedspeakers: DaphneKoller, HeikkiMannila, andJ. RossQuinlan. ThanksareduetoTanjaUrban ci candherteamandMajda Zidanskiandherteamfortheorganizationalsupportprovided. Wewishtothank AlfredHofmannandAnnaKramerofSpringer-Verlagfortheircooperationin publishing these proceedings. Finally, we gratefully acknowledge the nancial supportprovidedbythesponsorsofILP-99. April1999 Sa soD zeroski PeterFlach ILP-99ProgramCommittee FrancescoBergadano(UniversityofTorino) HenrikBostr]om(UniversityofStockholm) IvanBratko(UniversityofLjubljana) WilliamCohen(AT&TResearchLabs) JamesCussens(UniversityofYork) LucDeRaedt(UniversityofLeuven) Sa soD zeroski(Jo zefStefanInstitute, co-chair) PeterFlach(UniversityofBristol, co-chair) AlanFrisch(UniversityofYork) KoichiFurukawa(KeioUniversity) RoniKhardon(UniversityofEdinburgh) NadaLavra c(Jo zefStefanInstitute) JohnLloyd(AustralianNationalUniversity) StanMatwin(UniversityofOttawa) RaymondMooney(UniversityofTexas) StephenMuggleton(UniversityofYork) Shan-HweiNienhuys-Cheng(UniversityofRotterdam) DavidPage(UniversityofLouisville) BernhardPfahringer(AustrianResearchInstituteforAI) CelineRouveirol(UniversityofParis) ClaudeSammut(UniversityofNewSouthWales) MicheleSebag(EcolePolytechnique) AshwinSrinivasan(UniversityofOxford) PrasadTadepalli(OregonStateUniversity) StefanWrobel(GMDResearchCenterforInformationTechnology) OrganizationalSupport TheAlbatrossCongressTouristAgency, Bled Center for Knowledge Transfer in Information Technologies, Jo zef Stefan Institute, Ljubljana SponsorsofILP-99 ILPnet2, NetworkofExcellenceinInductiveLogicProgramming COMPULOGNet, EuropeanNetworkofExcellenceinComputationalLogic Jo zefStefanInstitute, Ljubljana LPASoftware, Inc. UniversityofBristol TableofContents I InvitedPapers ProbabilisticRelationalModels D. Koller . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 InductiveDatabases(Abstract) H. Mannila. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 SomeElementsofMachineLearning(ExtendedAbstract) J. R. Quinlan. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 II ContributedPapers Re nementOperatorsCanBe(Weakly)Perfect L. Badea, M. Stanciu. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 CombiningDivide-and-ConquerandSeparate-and-ConquerforE cientand E ectiveRuleInduction H. Bostr]om, L. Asker. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 Re ningCompleteHypothesesinILP I. Bratko. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 AcquiringGraphicDesignKnowledge withNonmonotonicInductiveLearning K. Chiba, H. Ohwada, F. Mizoguchi. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56 MorphosyntacticTaggingofSloveneUsingProgol J. Cussens, S. D zeroski, T. Erjavec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68 ExperimentsinPredictingBiodegradability S. D zeroski, H. Blockeel, B. Kompare, S. Kramer, B. Pfahringer, W. VanLaer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 1BC: AFirst-OrderBayesianClassi er P. Flach, N. Lachiche. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 92 SortedDownwardRe nement: BuildingBackgroundKnowledge intoaRe nementOperatorforInductiveLogicProgramming A. M. Frisch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 104 AStrongCompleteSchemaforInductiveFunctionalLogicProgramming J. Hern andez-Orallo, M. J. Ram rez-Quintana. . . . . . . . . . . . . . . . . . . . . . . . . . . . 116 ApplicationofDi erentLearningMethods toHungarianPart-of-SpeechTagging T. Horv ath, Z. Alexin, T. Gyim othy, S. Wrobel . . . . . . . . . . . . . . . . . . . . . . . . . . 128 VIII TableofContents CombiningLAPISandWordNetfortheLearningofLRParserswith OptimalSemanticConstraints D. Kazakov. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140 LearningWordSegmentationRulesforTagPrediction D. Kazakov, S. Manandhar, T. Erjavec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 152 ApproximateILPRulesbyBackpropagationNeuralNetwork: AResultonThaiCharacterRecognition B. Kijsirikul, S. Sinthupinyo. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 162 RuleEvaluationMeasures: AUnifyingView N. Lavra c, P. Flach, B. Zupan. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174 ImprovingPart-of-SpeechDisambiguationRulesbyAdding LinguisticKnowledge N. Lindberg, M. Eineborg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 186 OnSu cientConditionsforLearnabilityofLogicProgramsfrom Positi