[Natural.Language.Annotation.for.Machine.Learning(Early.Release)].James.Pustejovsky.文字版

《[Natural.Language.Annotation.for.Machine.Learning(Early.Release)].James.Pustejovsky.文字版》由会员上传分享，免费在线阅读，更多相关内容在学术论文-天天文库。

1、NaturalLanguageAnnotationforMachineLearningJamesPustejovskyandAmberStubbsBeijing•Cambridge•Farnham•Köln•Sebastopol•TokyoNaturalLanguageAnnotationforMachineLearningbyJamesPustejovskyandAmberStubbsRevisionHistoryforthe:2012-03-06Earlyreleaserevision12012-03-26Earlyr

2、eleaserevision2Seehttp://oreilly.com/catalog/errata.csp?isbn=9781449306663forreleasedetails.ISBN:978-1-449-30666-31332788036TableofContentsPreface......................................................................v1.TheBasics....................................

3、.........................1TheImportanceofLanguageAnnotation1TheLayersofLinguisticDescription2WhatisNaturalLanguageProcessing?4ABriefHistoryofCorpusLinguistics5WhatisaCorpus?7EarlyUseofCorpora9CorporaToday12KindsofAnnotation13LanguageDataandMachineLearning18Classif

4、ication19Clustering19StructuredPatternInduction19TheAnnotationDevelopmentCycle20Modelthephenomenon21AnnotatewiththeSpecification24TrainandTestthealgorithmsoverthecorpus25Evaluatetheresults26RevisetheModelandAlgorithms27Summary282.DefiningYourGoalandDataset........

5、..................................31Definingagoal31TheStatementofPurpose32RefiningyourGoal:InformativityversusCorrectness33Backgroundresearch38LanguageResources39OrganizationsandConferences39NLPChallenges40iiiAssemblingyourdataset40CollectingdatafromtheInternet41E

6、licitingdatafrompeople41Preparingyourdataforannotation42Metadata42Pre-processeddata43Thesizeofyourcorpus44ExistingCorpora44Distributionswithincorpora45Summary473.BuildingYourModelandSpecification....................................49SomeExampleModelsandSpecs49Film

7、genreclassification52AddingNamedEntities53SemanticRoles54Adopting(ornotAdopting)ExistingModels55CreatingyourownModelandSpecification:GeneralityversusSpecif-icity56UsingExistingModelsandSpecifications58UsingModelswithoutSpecifications59DifferentKindsofStandards60IS

8、OStandards60Community-drivenstandards63Otherstandardsaffectingannotation63Summary644.ApplyingandAdoptingAnnotationStandardstoyourModel..................