Index

A

• Annotator options
  • URL / Using the Stanford pipeline
• annotators
  • about / Extracting relationships
• Annotator tags
  • about / Using the StanfordLemmatizer class
• Apache OpenNLP
  • about / Apache OpenNLP
• APIs
  • used, for classifying text / Using APIs to classify text
  • OpenNLP, using / Using OpenNLP
  • Stanford API, using / Using Stanford API
  • LingPipe, used for classifying text / Using LingPipe to classify text
• application areas, NLP
  • searching / Why use NLP?
  • machine translation / Why use NLP?
  • summation / Why use NLP?
  • Named Entity Recognition (NER) / Why use NLP?
  • information grouping / Why use NLP?
  • Parts-of-Speech Tagging (POS) / Why use NLP?
  • sentiment analysis / Why use NLP?
  • answering queries / Why use NLP?
  • speech recognition / Why use NLP?
  • Natural Language Generation / Why use NLP?

B

• Boilerpipe
  • URL / Preparing data
  • used, for text extraction from HTML / Using Boilerpipe to extract text from HTML
• BreakIteator class
  • using / Using the BreakIterator class
  • first method / Using the BreakIterator class
  • next method / Using the BreakIterator class
  • previous method / Using the BreakIterator class
  • DONE method / Using the BreakIterator class
• BreakIterator class
  • using / Using the BreakIterator class
• BreakIterator methods
  • about / Using the BreakIterator class

C

• character processing
  • about / Preparing data
• chunking
  • about / Techniques for name recognition
• classification
  • about / Classifying text and documents
  • using / How classification is used
• classifier
  • about / Text classifying techniques
  • URL / Using Stanford API
• clustering
  • about / Classifying text and documents
• Conditional Random Field (CRF) sequence model
  • about / Using the Stanford API for NER
• coreference resolution entities
  • finding / Finding coreference resolution entities
• coreferences resolution
  • about / Why is NLP so hard?
• CoreLabelTokenFactory class
  • about / Stanford NLP
• corpora
  • reference link / The tagging process

D

• data
  • preparing / Preparing data
• data, NLP
  • preparing / Preparing data
• DBPedia
  • URL / Using extracted relationships
• Delimiter
  • specifying / Specifying the delimiter
• Delimiters
  • about / Finding parts of text
• DocumentPreprocessor class
  • using / Using the DocumentPreprocessor class, Using the DocumentPreprocessor class
  • setElementDelimiter method / Using the DocumentPreprocessor class
  • setSentenceDelimiter method / Using the DocumentPreprocessor class
  • setSentenceFinalPuncWords method / Using the DocumentPreprocessor class
  • setKeepEmptySentences method / Using the DocumentPreprocessor class

E

• encodings / Preparing data
• endophora
  • about / Finding coreference resolution entities
• ExactDictionaryChunker class
  • using / Using the ExactDictionaryChunker class
• extracted relationships
  • using / Using extracted relationships
  • Resource Description Framework (RDF) / Using extracted relationships
  • DBPedia / Using extracted relationships

F

• flags, HeuristicSentenceModel class
  • Balance Parentheses / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
  • Force Final Boundary / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
• Freebase
  • URL / Relationship types

G

• GATE
  • about / GATE
  • references / GATE
  • URL / Using the MaxentTagger class to tag textese
• General Inquirer
  • URL / Understanding sentiment analysis
• GrammarScope
  • URL / Understanding parse trees
• GrammaticalStructure class
  • used, for finding word dependencies / Finding word dependencies using the GrammaticalStructure class

H

• Hidden Markov Models (HMM)
  • about / The tagging process
• HmmDecoder class
  • using, with Best_First tags / Using the HmmDecoder class with Best_First tags
  • using, with NBest tags / Using the HmmDecoder class with NBest tags
  • tag confidences, determining / Determining tag confidence with the HmmDecoder class

I

• IBM Word Cloud Generator
  • URL / How classification is used
• IndoEuropeanSentenceModel class
  • using / Using the IndoEuropeanSentenceModel class

J

• Java's regular expressions
  • used, for searching entities / Using Java's regular expressions to find entities
• Java core tokenization techniques
  • URL / Performance considerations with java core tokenization
• Java tokenizers
  • about / Simple Java tokenizers
  • Scanner class, using / Using the Scanner class
  • split method, using / Using the split method
  • BreakIterator class, using / Using the BreakIterator class
  • StreamTokenizer class, using / Using the StreamTokenizer class
  • StringTokenizer class, using / Using the StringTokenizer class
  • performance considerations / Performance considerations with java core tokenization

K

• k-nearest neighbor
  • about / Text classifying techniques

L

• Leipzig Corpora Collection
  • URL / Language identification using LingPipe
• lemma
  • about / Why is NLP so hard?
• lemmatization
  • about / Using stemming
  • using / Using lemmatization
  • StanfordLemmatizer class, using / Using the StanfordLemmatizer class
  • used, in OpenNLP / Using lemmatization in OpenNLP
• Lemmatization
  • about / Why is NLP so hard?
• LexedTokenFactory interface
  • about / Stanford NLP
• LexicalizedParser class
  • using / Using the LexicalizedParser class
• LingPipe
  • about / LingPipe
  • references / LingPipe
  • using / Using LingPipe
  • IndoEuropeanSentenceModel class, using / Using the IndoEuropeanSentenceModel class
  • SentenceChunker class, using / Using the SentenceChunker class
  • MedlineSentenceModel class, using / Using the MedlineSentenceModel class
  • using, for NER / Using LingPipe for NER
  • name entity models, using / Using LingPipe's name entity models
  • ExactDictionaryChunker class, using / Using the ExactDictionaryChunker class
  • text training, Classified class used / Training text using the Classified class
  • training categories, using / Using other training categories
  • used, for classifying text / Classifying text using LingPipe
  • used, for sentiment analysis / Sentiment analysis using LingPipe
  • used, for Language Identification / Language identification using LingPipe
  • URL / Using NLP APIs
• LingPipe's HeuristicSentenceModel class
  • SBD rules / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
• LingPipe's RegExChunker class
  • using / Using LingPipe's RegExChunker class
• LingPipe POS taggers
  • using / Using LingPipe POS taggers
  • HmmDecoder class, using with Best_First tags / Using the HmmDecoder class with Best_First tags
  • HmmDecoder class, using with NBest tags / Using the HmmDecoder class with NBest tags
  • tag confidences, determining with HmmDecoder class / Determining tag confidence with the HmmDecoder class
• LingPipe tokenizers
  • using / Using LingPipe tokenizers
• lists
  • about / Lists and regular expressions

M

• MaxentTagger class
  • using / Using Stanford MaxentTagger
  • used, for tagging textese / Using the MaxentTagger class to tag textese
• Maximum Entropy (maxent) / Using the TokenizerME class
• MEDLINE / Using the MedlineSentenceModel class
• MedlineSentenceModel class
  • using / Using the MedlineSentenceModel class
• MLA handbook
  • URL / What makes SBD difficult?
• morpheme / Why is NLP so hard?
• morphology
  • about / Finding parts of text
• Multi-Purpose Internet Mail Extensions (MIME) type
  • about / Preparing data

N

• Naive Bayes
  • about / Text classifying techniques
• name entity models, LingPipe
  • using / Using LingPipe's name entity models
  • URL / Using LingPipe's name entity models
• NER
  • limitations / Why NER is difficult?
• NER model
  • training / Training a model
  • evaluating / Evaluating a model
• NER techniques
  • about / Techniques for name recognition
  • lists / Lists and regular expressions
  • regular expressions / Lists and regular expressions
  • statistical classifiers / Statistical classifiers
• newsgroups
  • URL / Using other training categories
  • about / Using other training categories
• NLP
  • about / What is NLP?
  • advantages / Why use NLP?
  • text analysis / Why use NLP?
  • limitations / Why is NLP so hard?
  • text processing tasks / Overview of text processing tasks
  • data, preparing / Preparing data
• NLP APIs / Preparing data
  • using / Using NLP APIs, Using NLP APIs
  • OpenNLP, using / Using OpenNLP, Using OpenNLP
  • using, for NER / Using NLP APIs
  • OpenNLP, using for NER / Using OpenNLP for NER
  • Stanford API, using for NER / Using the Stanford API for NER
  • LingPipe, using for NER / Using LingPipe for NER
  • using, for POS tagging / Using the NLP APIs
  • OpenNLP POS taggers, using / Using OpenNLP POS taggers
  • Stanford POS taggers, using / Using Stanford POS taggers
  • LingPipe POS taggers, using / Using LingPipe POS taggers
  • OpenNLP POSModel, training / Training the OpenNLP POSModel
  • Stanford API, using / Using the Stanford API
  • coreference resolution entities, finding / Finding coreference resolution entities
• NLP models
  • about / Understanding NLP models
  • task, identifying / Identifying the task
  • selecting / Selecting a model
  • building / Building and training the model
  • training / Building and training the model
  • verifying / Verifying the model
  • using / Using the model
• NLP Tokenizer APIs
  • about / NLP tokenizer APIs
  • OpenNLPTokenizer, using / Using the OpenNLPTokenizer class
  • Stanford Tokenizer, using / Using the Stanford tokenizer
• NLP tools
  • about / Survey of NLP tools
  • Apache OpenNLP / Apache OpenNLP
  • Stanford NLP / Stanford NLP
  • LingPipe / LingPipe
  • GATE / GATE
  • UIMA / UIMA
• normalization
  • defining / Understanding normalization
  • text, converting to lowercase / Converting to lowercase
  • stopwords, removing / Removing stopwords
  • stemming, using / Using stemming
  • lemmatization, using / Using lemmatization
• normalization techniques
  • combining, pipeline used / Normalizing using a pipeline

O

• OASIS / UIMA
• OpenNLP
  • references / Apache OpenNLP
  • lemmatization, using / Using lemmatization in OpenNLP
  • using / Using OpenNLP, Using OpenNLP, Using OpenNLP
  • SentenceDetectorME class, using / Using the SentenceDetectorME class
  • sentPosDetect method, using / Using the sentPosDetect method
  • using, for NER / Using OpenNLP for NER
  • accuracy, determining of entity / Determining the accuracy of the entity
  • other entity types, using / Using other entity types
  • URL, for NER models / Using other entity types
  • multiple entity types, processing / Processing multiple entity types
  • classification model, training / Training an OpenNLP classification model
  • DocumentCategorizerME class used, for classifying text / Using DocumentCategorizerME to classify text
• OpenNLP chunking
  • using / Using OpenNLP chunking
• OpenNLP POSModel
  • training / Training the OpenNLP POSModel
• OpenNLP POSTaggerME class
  • using / Using the OpenNLP POSTaggerME class for POS taggers
• OpenNLP POS taggers
  • using / Using OpenNLP POS taggers
  • OpenNLP POSTaggerME class, using / Using the OpenNLP POSTaggerME class for POS taggers
  • OpenNLP chunking, using / Using OpenNLP chunking
  • POSDictionary class, using / Using the POSDictionary class
• OpenNLPTokenizer
  • using / Using the OpenNLPTokenizer class
  • tokenize / Using the OpenNLPTokenizer class
  • tokenizePos / Using the OpenNLPTokenizer class
  • SimpleTokenizer class, using / Using the SimpleTokenizer class
  • WhitespaceTokenizer class, using / Using the WhitespaceTokenizer class
  • TokenizerME class, using / Using the TokenizerME class
• open source APIs
  • references / Survey of NLP tools

P

• parse trees
  • defining / Understanding parse trees
• Parsing
  • about / Detecting Parts of Speech
• parsing
  • about / Importance of POS taggers
• parsing types
  • dependency / Relationship types
  • phrase structure / Relationship types
• Parts of Speech (POS)
  • detecting / Detecting Parts of Speech
• parts of text
  • defining / Understanding the parts of text
• PDFBox
  • URL / Preparing data
  • used, for text extraction from PDF documents / Using PDFBox to extract text from PDF documents
• Penn TreeBank
  • URL / Using the LexicalizedParser class
• Penn Treebank 3 (PTB) tokenizer
  • URL / Using the PTBTokenizer class
• periods / What makes SBD difficult?
• pipeline
  • about / Survey of NLP tools
  • using / Using a pipeline
  • used, for combining normalization techniques / Normalizing using a pipeline
• pipelines
  • about / Pipelines
  • advantages / Pipelines
  • Stanford pipeline, using / Using the Stanford pipeline
  • multiple cores, using with Stanford pipeline / Using multiple cores with the Stanford pipeline
  • creating, for searching text / Creating a pipeline to search text
• POI
  • URL / Preparing data
  • used, for text extraction from word documents / Using POI to extract text from Word documents
• Porter Stemmer
  • using / Using the Porter Stemmer
• PorterStemmer class
  • methods / Using the Porter Stemmer
• POSDictionary class
  • using / Using the POSDictionary class
  • tag dictionary, obtaining / Obtaining the tag dictionary for a tagger
  • word's tags, determining / Determining a word's tags
  • word's tags, modifying / Changing a word's tags
  • new tag dictionary, adding / Adding a new tag dictionary
  • new tag dictionary, creating from file / Creating a dictionary from a file
• POS models, LingPipe
  • URL / Using LingPipe POS taggers
• POS models, OpenNLP
  • URL / Using the OpenNLP POSTaggerME class for POS taggers
• POS tagging
  • about / The tagging process
  • Rule-based approach / The tagging process
  • Stochastic approach / The tagging process
  • benefits / Importance of POS taggers
  • limitations / What makes POS difficult?
• POS tags
  • about / Using lemmatization in OpenNLP
  • URL / Using lemmatization in OpenNLP
• PTBTokenizer class
  • using / Using the PTBTokenizer class, Using the PTBTokenizer class
  • invertible method / Using the PTBTokenizer class
  • tokenizeNLs method / Using the PTBTokenizer class
  • americanize method / Using the PTBTokenizer class
  • normalizeAmpersandEntity method / Using the PTBTokenizer class
  • normalizeFractions method / Using the PTBTokenizer class
  • asciiQuotes method / Using the PTBTokenizer class
  • unicodeQuotes method / Using the PTBTokenizer class
• punctuation ambiguity / What makes SBD difficult?

Q

• question type
  • determining / Determining the question type

R

• Regexper
  • URL / Using regular expressions
• regular expressions
  • about / Survey of NLP tools, Lists and regular expressions
  • using / Using regular expressions
  • reference link, of example / Using regular expressions
  • using, for NER / Using regular expressions for NER
  • Java's regular expressions, using / Using Java's regular expressions to find entities
  • LingPipe's RegExChunker class, using / Using LingPipe's RegExChunker class
• regular expressions library
  • URL / Using regular expressions for NER
• relationships
  • extracting / Extracting relationships
  • extracting, for question-answer system / Extracting relationships for a question-answer system
• relationships, for question-answer system
  • word dependencies, finding / Finding the word dependencies
  • question type, determining / Determining the question type
  • answer, searching / Searching for the answer
• relationship types
  • about / Relationship types
• Resource Description Framework (RDF)
  • URL / Using extracted relationships
• Rotten Tomatoes
  • URL / Using the Stanford pipeline to perform sentiment analysis
• rule-based classification / Text classifying techniques

S

• SBD
  • limitations / What makes SBD difficult?
• SBD process
  • about / The SBD process
• SBD rules, LingPipe's HeuristicSentenceModel class / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
• Scanner class
  • using / Using the Scanner class
  • Delimiter, specifying / Specifying the delimiter
• Sentence Boundary Disambiguation (SBD)
  • about / Finding sentences
• SentenceChunker class
  • using / Using the SentenceChunker class
• SentenceDetectorEvaluator class
  • used, for evaluating Sentence Detector model / Evaluating the model using the SentenceDetectorEvaluator class
• SentenceDetectorME class
  • using / Using the SentenceDetectorME class
  • parameters / Training a Sentence Detector model
• Sentence Detector model
  • training / Training a Sentence Detector model
  • Trained model, using / Using the Trained model
  • evaluating, SentenceDetectorEvaluator class used / Evaluating the model using the SentenceDetectorEvaluator class
• sentiment analysis
  • about / How classification is used
  • defining / Understanding sentiment analysis
  • performing, LingPipe used / Sentiment analysis using LingPipe
• sentPosDetect method
  • using / Using the sentPosDetect method
• simple Java SBDs
  • about / Simple Java SBDs
  • regular expressions, using / Using regular expressions
  • BreakIteator class, using / Using the BreakIterator class
• SimpleTokenizer class
  • using / Using the SimpleTokenizer class
• Span methods
  • contains / Using the sentPosDetect method
  • crosses / Using the sentPosDetect method
  • length / Using the sentPosDetect method
  • startsWith / Using the sentPosDetect method
• split method
  • using / Using the split method
• Stanford
  • references / Stanford NLP
• Stanford API
  • using / Using the Stanford API, Using Stanford API, Using the Stanford API
  • PTBTokenizer class, using / Using the PTBTokenizer class
  • DocumentPreprocessor class, using / Using the DocumentPreprocessor class
  • StanfordCoreNLP class, using / Using the StanfordCoreNLP class
  • using, for NER / Using the Stanford API for NER
  • ColumnDataClassifier class, used for classification / Using the ColumnDataClassifier class for classification
  • StanfordCoreNLP pipeline, used for performing sentiment analysis / Using the Stanford pipeline to perform sentiment analysis
  • LexicalizedParser class, using / Using the LexicalizedParser class
  • TreePrint class, using / Using the TreePrint class
  • word dependencies, finding / Finding word dependencies using the GrammaticalStructure class
• Stanford CoreNLP
  • about / Stanford NLP
• StanfordCoreNLP class
  • using / Using the StanfordCoreNLP class
• StanfordLemmatizer class
  • using / Using the StanfordLemmatizer class
• Stanford NLP
  • about / Stanford NLP
• Stanford pipeline
  • using / Using Stanford pipeline to perform tagging, Using the Stanford pipeline
  • multiple cores, using with / Using multiple cores with the Stanford pipeline
• Stanford POS taggers
  • using / Using Stanford POS taggers
  • MaxentTagger class, using / Using Stanford MaxentTagger
  • Stanford pipeline, using / Using Stanford pipeline to perform tagging
• Stanford Tokenizer
  • using / Using the Stanford tokenizer
  • PTBTokenizer class, using / Using the PTBTokenizer class
  • DocumentPreprocessor class, using / Using the DocumentPreprocessor class
  • pipeline, using / Using a pipeline
  • LingPipe tokenizers, using / Using LingPipe tokenizers
• statistical classifiers
  • about / Statistical classifiers
• stemming
  • about / Why is NLP so hard?
  • using / Using stemming
  • Porter Stemmer, using / Using the Porter Stemmer
  • with LingPipe / Stemming with LingPipe
• stopwords
  • URL / What is tokenization?
  • about / What is tokenization?
  • removing / Removing stopwords
  • StopWords class, creating / Creating a StopWords class
  • removing, LingPipe used / Using LingPipe to remove stopwords
• StopWords class
  • creating / Creating a StopWords class
  • members / Creating a StopWords class
• StreamTokenizer class
  • using / Using the StreamTokenizer class
  • fields / Using the StreamTokenizer class
• StringTokenizer class
  • using / Using the StringTokenizer class
• summarization
  • about / Why is NLP so hard?
• Supervised Machine Learning (SML) / Text classifying techniques
• Support-Vector Machine (SVM)
  • about / Text classifying techniques

T

• tag
  • about / The tagging process
• tagging
  • about / The tagging process
• tag set
  • about / The tagging process
  • reference link / The tagging process
• text
  • extracting / Preparing data
• Text Analytics
  • about / Extracting relationships
• text classifying techniques
  • about / Text classifying techniques
  • rule-based classification / Text classifying techniques
  • Supervised Machine Learning (SML) / Text classifying techniques
• textese
  • about / What makes POS difficult?
  • reference link / What makes POS difficult?
• text extraction
  • Boilerpipe, using from HTML / Using Boilerpipe to extract text from HTML
  • POI, using from word documents / Using POI to extract text from Word documents
  • PDFBox, using from PDF documents / Using PDFBox to extract text from PDF documents
• text processing tasks
  • overview / Overview of text processing tasks
  • parts of texts, finding / Finding parts of text
  • sentences, finding / Finding sentences
  • people and things, finding / Finding people and things
  • Parts of Speech (POS), detecting / Detecting Parts of Speech
  • text and documents, classifying / Classifying text and documents
  • relationships, extracting / Extracting relationships
  • combined approaches, using / Using combined approaches
• text search
  • pipeline, creating for / Creating a pipeline to search text
• tokenization
  • about / Why is NLP so hard?, Finding parts of text, What is tokenization?
• tokenization, factors
  • language / What is tokenization?
  • text format / What is tokenization?
  • stopwords / What is tokenization?
  • Text Expansion / What is tokenization?
  • case / What is tokenization?
  • stemming / What is tokenization?
  • lemmatization / What is tokenization?
• tokenizer
  • training, for finding parts / Training a tokenizer to find parts of text
• TokenizerME class
  • using / Using the TokenizerME class
• tokenizers
  • uses / Uses of tokenizers
  • comparing / Comparing tokenizers
• TokenME class
  • parameters / Training a tokenizer to find parts of text
• Tokens / Why is NLP so hard?
• tokens, HeuristicSentenceModel class
  • Possible Stops / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
  • Impossible Penultimates / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
  • Impossible Starts / Understanding SBD rules of LingPipe's HeuristicSentenceModel class
• Trained model
  • using / Using the Trained model
• train method
  • parameters / Training a tokenizer to find parts of text
• Treebank
  • about / Finding word dependencies using the GrammaticalStructure class
  • URL / Finding word dependencies using the GrammaticalStructure class
• TreePrint class
  • using / Using the TreePrint class

U

• UIMA
  • about / UIMA
  • references / UIMA

W

• WhitespaceTokenizer class
  • using / Using the WhitespaceTokenizer class
• word dependencies
  • finding, GrammaticalStructure class used / Finding word dependencies using the GrammaticalStructure class
  • finding / Finding the word dependencies
• WordNet thesaurus
  • URL / Relationship types
• words, classifying
  • simple words / Finding parts of text
  • morphemes / Finding parts of text
  • prefix/suffix / Finding parts of text
  • synonyms / Finding parts of text
  • abbreviations / Finding parts of text
  • acronyms / Finding parts of text
  • contractions / Finding parts of text
  • numbers / Finding parts of text
• Word Sense Disambiguation
  • about / Why is NLP so hard?
• WordTokenFactory class
  • about / Stanford NLP