搜索引擎

1SearchEnginesandInformationRetrieval

1.1WhatIsInformationRetrieval？

1.2TheBigIssues

1.3SearchEngines

1.4SearchEngineers

2ArchitectureofaSearchEngine

2.1WhatIsanArchitecture？

2.2BasicBuildingBlocks

2.3BreakingItDown

2.3.1TextAcquisition

2.3.2TextTransformation

2.3.3IndexCreation

2.3.4UserInteraction

2.3.5Ranking

2.3.6Evaluation

2.4HowDoesItReallyWork？

3CrawlsandFeeds

3.1DecidingWhattoSearch

3.2CrawlingtheWeb

3.2.1RetrievingWebPages

3.2.2TheWebCrawler

3.2.3Freshness

3.2.4FocusedCrawling

3.2.5DeepWeb

3.2.6Sitemaps

3.2.7DistributedCrawling

3.3CrawlingDocumentsandEmail

3.4DocumentFeeds

3.5TheConversionProblem

3.5.1CharacterEncodings

3.6StoringtheDocuments

3.6.1UsingaDatabaseSystem

3.6.2RandomAccess

3.6.3CompressionandLargeFiles

3.6.4Update

3.6.5BigTable

3.7DetectingDuplicates

3.8RemovingNoise

4ProcessingText

4.1FromWordstoTerms

4.2TextStatistics

4.2.1VocabularyGrowth

4.2.2EstimatingCollectionandResultSetSizes

4.3DocumentParsing

4.3.1Overview

4.3.2Tokenizing

4.3.3Stopping

4.3.4Stemming

4.3.5PhrasesandN-grams

4.4DocumentStructureandMarkup

4.5LinkAnalysis

4.5.1AnchorText

4.5.2PageRank

4.5.3LinkQuality

4.6InformationExtraction

4.6.1HiddenMarkovModelsforExtraction

4.7Internationalization

5RankingwithIndexes

5.1Overview

5.2AbstractModelofRanking

5.3InvertedIndexes

5.3.1Documents

5.3.2Counts

5.3.3Positions

5.3.4FieldsandExtents

5.3.5Scores

5.3.6Ordering

5.4Compression

5.4.1EntropyandAmbiguity

5.4.2DeltaEncoding

5.4.3Bit-AlignedCodes

5.4.4Byte-AlignedCodes

5.4.5CompressioninPractice

5.4.6LookingAhead

5.4.7SkippingandSkipPointers

5.5AuxiliaryStructures

5.6IndexConstruction

5.6.1SimpleConstruction

5.6.2Merging

5.6.3ParallelismandDistribution

5.6.4Update

5.7QueryProcessing

5.7.1Document-at-a-timeEvaluation

5.7.2Term-at-a-timeEvaluation

5.7.3OptimizationTechniques

5.7.4StructuredQueries

5.7.5DistributedEvaluation

5.7.6Caching

6QueriesandInterfaces

6.1InformationNeedsandQueries

6.2QueryTransformationandRefinement

6.2.1StoppingandStemmingRevisited

6.2.2SpellCheckingandSuggestions

6.2.3QueryExpansion

6.2.4RelevanceFeedback

6.2.5ContextandPersonalization

6.3ShowingtheResults

6.3.1ResultPagesandSnippets

6.3.2AdvertisingandSearch

6.3.3ClusteringtheResults

6.4Cross-LanguageSearch

7RetrievalModels

7.1OverviewofRetrievalModels

7.1.1BooleanRetrieval

7.1.2TheVectorSpaceModel

7.2ProbabilisticModels

7.2.1InformationRetrievalasClassification

7.2.2TheBM25RankingAlgorithm

7.3RankingBasedonLanguageModels

7.3.1QueryLikelihoodRanking

7.3.2RelevanceModelsandPseudo-RelevanceFeedback

7.4ComplexQueriesandCombiningEvidence

7.4.1TheInferenceNetworkModel

7.4.2TheGalagoQueryLanguage

7.5WebSearch

7.6MachineLearningandInformationRetrieval

7.6.1LearningtoRank

7.6.2TopicModelsandVocabularyMismatch

7.7Application-BasedModels

8EvaluatingSearchEngines

8.1WhyEvaluate？

8.2TheEvaluationCorpus

8.3Logging

8.4EffectivenessMetrics

8.4.1RecallandPrecision

8.4.2AveragingandInterpolation

8.4.3FocusingontheTopDocuments

8.4.4UsingPreferences

8.5EfficiencyMetrics

8.6Training,Testing,andStatistics

8.6.1SignificanceTests

8.6.2SettingParameterValues

8.6.3OnlineTesting

8.7TheBottomLine

9ClassificationandClustering

9.1ClassificationandCategorization

9.1.1NaiveBayes

9.1.2SupportVectorMachines

9.1.3Evaluation

9.1.4ClassifierandFeatureSelection

9.1.5Spam,Sentiment,andOnlineAdvertising

9.2Clustering

9.2.1HierarchicalandK-MeansClustering

9.2.2KNearestNeighborClustering

9.2.3Evaluation

9.2.4HowtoChooseK

9.2.5ClusteringandSearch

10SocialSearch

10.1WhatIsSocialSearch？

10.2UserTagsandManualIndexing

10.2.1SearchingTags

10.2.2InferringMissingTags

10.2.3BrowsingandTagClouds

10.3SearchingwithCommunities

10.3.1WhatIsaCommunity？

10.3.2FindingCommunities

10.3.3Community-BasedQuestionAnswering

10.3.4CollaborativeSearching

10.4FilteringandRecommending

10.4.1DocumentFiltering

10.4.2CollaborativeFiltering

10.5Peer-to-PeerandMetasearch

10.5.1DistributedSearch

10.5.2P2PNetworks

11BeyondBagofWords

11.1Overview

11.2Feature-BasedRetrievalModels

11.3TermDependenceModels

11.4StructureRevisited

11.4.1XMLRetrieval

11.4.2EntitySearch

11.5LongerQuestions,BetterAnswers

11.6Words,Pictures,andMusic

11.7OneSearchFitsAll？

References

Index

　　这是本全英文版本的信息检索知识读本。主要介绍了信息检索(IR)中的11个关键问题以及其如何影响搜索引擎的设计与实现，并且用数学模型强化了重要的概念。本书内容丰富，针对性、实用性较强，适合作为高等院校计算机科学或计算机工程专业的本科生、研究生的教材使用。　　本书介绍了信息检索(IR)中的关键问题，以及这些问题如何影响搜索引擎的设计与实现，并且用数学模型强化了重要的概念。对于网络搜索引擎这一重要的话题，书中主要涵盖了在网络上广泛使用的搜索技术。　　本书适用于高等院校计算机科学或计算机工程专业的本科生、研究生，对于专业人士而言，本书也不失为一本理想的入门教材。【作者简介】　　W.BruceCroft马萨诸塞大学阿默斯特分校计算机科学特聘教授、ACM会士。他创建了智能信息检索研究中心，发表了200余篇论文，多次获奖，其中包括2003年由ACMSIGIR颁发的GerardSalton奖。