|
||||||||||
| PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES | |||||||||
| Interface Summary | |
|---|---|
| DisambiguationRulesI | Container for disambiguation rules (between two NE types) |
| FeatureRepresentation | |
| LexiconOnDiskI | Lexicon loader |
| NamedEntityTypeEnumI | NE type enumeration |
| TokenFeature.IFeature | a feature must have a type and a mechanism that compute its value |
| TokenFeature.Mechanism | Each feature must implements one mechanism |
| Class Summary | |
|---|---|
| AbbreviationLookup | Wraps around a hashtable that contains a list of abbreviation. |
| AccentLookup | Lookup for accent equivalences |
| Balie | This is the main entry point for training Balie. |
| Canonizer | Offers static function to convert a word into its canon form. |
| CharacterNGram | Methods to collect and handle character n-gram. |
| CombinationGenerator | |
| DebugInfo | Class that group routines for debugging. |
| DisambiguationRulesKey | A key is made of two NE types |
| DisambiguationRulesNerf | |
| DisambiguationRulesOutcome | |
| FeatureRepresentationNominal | |
| FeatureRepresentationVocabulary | |
| FileHandler | Simple file loader |
| HashCodeUtil | Collected methods which allow easy implementation of hashCode. |
| LanguageIdentification | Methods for training, testing and using language identification. |
| LanguageIdentificationGuess | A guess is compose of a language (e.g.: French) along with its probability (ex.: 0.9). |
| LanguageSpecific | Squeleton of language specific routines. |
| LanguageSpecificEnglish | Routines specific to English language. |
| LanguageSpecificFrench | Routines specific to French language. |
| LanguageSpecificGerman | Routines specific to German language. |
| LanguageSpecificItalian | Routines specific to Italian language. |
| LanguageSpecificRomanian | Routines specific to Romanian language. |
| LanguageSpecificSpanish | Routines specific to Spanish language. |
| LexiconOnDisk | Lexicon loader for baseline NER |
| LigatureLookup | Wraps around a hashtable that contains a list of ligatures. |
| NamedEntityAlias | NE alias object is a set of labels that represent the same entity |
| NamedEntityExplanation | |
| NamedEntityExplanation.Acronym | |
| NamedEntityExplanation.AdjacentShareType | |
| NamedEntityExplanation.AliasDominantType | |
| NamedEntityExplanation.Classifier | |
| NamedEntityExplanation.ClassifierVote | |
| NamedEntityExplanation.EntityCapitalMerging | |
| NamedEntityExplanation.EntityEntityMerging | |
| NamedEntityExplanation.EntityPunctMerging | |
| NamedEntityExplanation.FuzzyMatch | |
| NamedEntityExplanation.LexiconLookup | |
| NamedEntityExplanation.NaturalLowercase | |
| NamedEntityExplanation.RejectedLowercasedAndUppercased | |
| NamedEntityExplanation.RejectedLowercasedOrAmbiguous | |
| NamedEntityExplanation.UnknownCapital | |
| NamedEntityRecognition | NER abstract class |
| NamedEntityRecognitionBase | BASE CLASS Named Entity Recognition (NER). |
| NamedEntityRecognitionNerf | NER extended with NERF disambiguation rules. |
| NamedEntityType | Type of a NE |
| PunctLookup | Wraps around a hashtable that contains a list of punctuation. |
| SBRCorpusHandler | SAX parser for the Sentence Boundary Recognition corpus. |
| SentenceBoundariesRecognition | Methods for training, testing and using sentence boundary recognition. |
| Token | Tokens are the unit element of Balie. |
| TokenConsts | Static class containing enumeration of token type value. |
| TokenFeature | This class contains a wide range of features about a token. |
| TokenFeature.BooleanMechanism | Mechanism for a boolean feature |
| TokenFeature.NominalMechanism | Mechanism for a nominal feature |
| TokenFeature.NumericMechanism | Mechanism for a numeric feature |
| Tokenizer | The tokenizer takes a text in input and extract a tokenlist. |
| TokenList | List of Tokens to represent a text. |
| TokenListIterator | Iterator for token list |
| UnbreakableLookup | Wraps around a hashtable that contains a list of Unbreakable tokens. |
| WekaAttribute | Wrapper around the Weka attributes. |
| WekaAttributeSelection | Methods to select the top attributes from a given classification problem. |
| WekaLearner | Methods to create, train and test a classification algorithm. |
| WekaPersistance | Service class to load and save Weka models. |
| XmlUtil | Utility class for reading and writing XML files |
| Enum Summary | |
|---|---|
| LexiconOnDisk.Lexicon | Choice of lexicons |
| NamedEntityTypeEnum | |
| NamedEntityTypeEnumMappingNerf | |
| TokenFeature.Feature | lexical features |
| TokenFeature.FeatureType | possible types for a token feature |
|
||||||||||
| PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES | |||||||||