Processor

Abstract Value Members

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

Named Entity Recognition; 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; modifies the document in place.

Concrete Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def annotate(doc: Document): Document

Annotate the given document, returning an annotated document.
Annotate the given document, returning an annotated document. The default implementation is an NLP pipeline of side-effecting calls.
def annotate(text: String, keepText: Boolean = false): Document

Annotate the given text string, specify whether to retain the text in the resultant Document.
Annotate the given text string, specify whether to retain the text in the resultant Document.

Definition Classes
Processor → ProcessorAnnotator
def annotateFromSentences(sentences: Iterable[String], keepText: Boolean = false): Document

Annotate the given sentences, specify whether to retain the text in the resultant Document.
Annotate the given sentences, specify whether to retain the text in the resultant Document.

Definition Classes
Processor → ProcessorAnnotator
def annotateFromTokens(sentences: Iterable[Iterable[String]], keepText: Boolean = false): Document

Annotate the given tokens, specify whether to retain the text in the resultant Document.
Annotate the given tokens, specify whether to retain the text in the resultant Document.

Definition Classes
Processor → ProcessorAnnotator
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def preprocessSentences(origSentences: Iterable[String]): Iterable[String]

Runs preprocessText on each sentence.
Runs preprocessText on each sentence.

Definition Classes
ProcessorAnnotator
def preprocessText(origText: String): String

Hook to allow the preprocessing of input text.
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.
origText
The original input text
returns
The preprocessed text

Definition Classes
ProcessorAnnotator
def preprocessTokens(origSentences: Iterable[Iterable[String]]): Iterable[Iterable[String]]

Runs preprocessText on each token.
Runs preprocessText on each token.

Definition Classes
ProcessorAnnotator
def shutdownClient: Unit

Shutdown the current instance of the client, if any.
Shutdown the current instance of the client, if any.

Definition Classes
ProcessorCSController
def shutdownClientServer: Unit

Shutdown the remote processor server AND the current instance of the client.
Shutdown the remote processor server AND the current instance of the client.

Definition Classes
ProcessorCSController
def shutdownServer: Unit

Send the server a message to shutdown actors and terminate the server.
Send the server a message to shutdown actors and terminate the server.

Definition Classes
ProcessorCSController
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Docs: object Processor | package processors

trait Processor extends ProcessorAnnotator

Abstract Value Members

abstract def chunking(doc: Document): Unit

abstract def discourse(doc: Document): Unit

abstract def lemmatize(doc: Document): Unit

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

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

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

abstract def parse(doc: Document): Unit

abstract def recognizeNamedEntities(doc: Document): Unit

abstract def resolveCoreference(doc: Document): Unit

abstract def tagPartsOfSpeech(doc: Document): Unit

Concrete Value Members

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]

def preprocessText(origText: String): String

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

def shutdownClient: Unit

def shutdownClientServer: Unit

def shutdownServer: Unit

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

Inherited from ProcessorAnnotator

Inherited from ProcessorCSController

Inherited from AnyRef

Inherited from Any

Ungrouped