All Classes

Class	Description
Annotation
AZDCDataset
BANNER
BANNER.MatchCriteria
BANNER.Performance
BANNER.PerformanceData
BANNERAnnotator
BANNERWrapper
BC2GMDataset
BEAT
BestMatchDisambiguator
ChemicalSuffix
CollectionsRand
Concept
ConceptName
CRFTagger
Dataset
Dataset.Tag
DictionaryTagger	This class represents a very simple dictionary-based tagger.
Entity
EntityIdentification
EntityName
EntityType	Instances of this class represent the type of a Mention.
ExtractAbbrev	This class was adapted from the BioText ExtractAbbrev.java software by Ariel S.
FeatureSet
FlattenPostProcessor
FlattenPostProcessor.FlattenType
Gazetteer	A Gazetteer allows read in a list of Entitys and their associated EntityNames from a file.
Gazetteer.EntityFilter
Index<K,V>
IndexedMentionIdentifier
IndexedMetricSetSimilarity<E,V>
JCoReEntityDataset
LChar	This class is used by the CRFTagger as the base for the feature set.
LemmaPOS	This class is used by the CRFTagger as the base for the feature set.
LocalAbbreviationPostProcessor
LowerCaseTokenText
Mention	Instances of this class represent the mention of an entity within a Sentence.
Mention.MentionType
MentionDisambiguator	Instances of this class make the final determination of which Entity a Mention refers.
MentionIdentifier	Instances of this class are responsible for determining a set of candidate Entity objects for each Mention.
MentionTypeHint	Taken from GNormPlus code: Wei, C.
NBestCRFTagger
OneSensePerDiscoursePostProcessor
OneSensePerDocument
ParenthesisPostProcessor	This class removes Mentions which contain a mismatched parenthesis ("(" or ")"), square bracket ("[" or "]") or curly bracket ("{" or "}").
PostProcessor	Instances of PostProcessor take Sentences which have been tagged and modify the set of Mentions according to some criteria.
Pretagger	This class is used by the CRFTagger as the base for the feature set.
ProteinSymbols	Taken from GNormPlus code: Wei, C.
RankedList<E>
RChar	This class is used by the CRFTagger as the base for the feature set.
Sentence	This class represents a single sentence, and provides for the text to be tokenized and for mentions.
Sentence.OverlapOption
Sentence2TokenSequence	This class is used by the CRFTagger as the base for the feature set.
SequentialPostProcessor
SetSimilarityMetric
SimFind	This class is used by the CRFTagger as the base for the distributional semantics features.
SimpleTokenizer	Tokens ouput by this tokenizer consist of a contiguous block of alphanumeric characters or a single punctuation mark.
TagFormat
Tagger	Taggers add Mentions to a Sentence which has been tokenized.
TagPosition
Text
ThresholdMentionProbabilityPostProcessor
Token	Represents a single token of text.
Tokenizer	Tokenizers take the text of a sentence and turn it into a Sentence object.
TokenLength
TokenNumberClass
TokenWeight	This class is used by the CRFTagger as the base for the feature set.
TokenWordClass
Trie<K,V>	A Trie (also known as a prefix tree) essentially maps from a list of objects (keys) to a value.
UMLSMetathesaurusDictionaryTagger
UnmodifiableArraySet<E>
Util