Processor

abstract def chunking(doc: Document): Unit

Shallow parsing; modifies the document in place

abstract def discourse(doc: Document): Unit

Discourse parsing; modifies the document in place

abstract def lemmatize(doc: Document): Unit

Lematization; modifies the document in place

abstract def mkDocument(text: String, keepText: Boolean = false): Document

Constructs a document of tokens from free text; includes sentence splitting and tokenization

abstract def mkDocumentFromSentences(sentences: Iterable[String], keepText: Boolean = false, charactersBetweenSentences: Int = 1): Document

Constructs a document of tokens from an array of untokenized sentences

abstract def mkDocumentFromTokens(sentences: Iterable[Iterable[String]], keepText: Boolean = false, charactersBetweenSentences: Int = 1, charactersBetweenTokens: Int = 1): Document

Constructs a document of tokens from an array of tokenized sentences

abstract def parse(doc: Document): Unit

Syntactic parsing; modifies the document in place

abstract def recognizeNamedEntities(doc: Document): Unit

NER; modifies the document in place

abstract def resolveCoreference(doc: Document): Unit

Coreference resolution; modifies the document in place

abstract def tagPartsOfSpeech(doc: Document): Unit

Part of speech tagging This modifies the document in place, which is not too elegant.

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def annotate(doc: Document): Document

def annotate(text: String, keepText: Boolean = false): Document

def annotateFromSentences(sentences: Iterable[String], keepText: Boolean = false): Document

def annotateFromTokens(sentences: Iterable[Iterable[String]], keepText: Boolean = false): Document

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def preprocessSentences(origSentences: Iterable[String]): Iterable[String]

Runs preprocessText on each sentence

def preprocessText(origText: String): String

Hook to allow the preprocessing of input text This is useful for domain-specific corrections, such as the ones in BioNLPProcessor, where we remove Table and Fig references Note that this is allowed to change character offsets

def preprocessTokens(origSentences: Iterable[Iterable[String]]): Iterable[Iterable[String]]

Runs preprocessText on each token

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit