FirebaseLanguageIdentification

public class FirebaseLanguageIdentification extends Object
implements Closeable

Entry point for Language Identification.

This class can be used from any thread.

Constant Summary

float	DEFAULT_IDENTIFY_LANGUAGE_CONFIDENCE_THRESHOLD	The default confidence threshold for the identifyLanguage(String) call.
float	DEFAULT_IDENTIFY_POSSIBLE_LANGUAGES_CONFIDENCE_THRESHOLD	The default confidence threshold for the identifyPossibleLanguages(String) call.
String	UNDETERMINED_LANGUAGE_CODE	The BCP-47 code for "undetermined language"

Public Method Summary

void	close() Releases resources when the client is finished using the instance.
Task<String>	identifyLanguage(String text) Identifies the language in a supplied String and returns the most likely language.
Task<List<IdentifiedLanguage>>	identifyPossibleLanguages(String text) Identifies the language in a supplied String and returns a list of possible languages, cutting off any languages whose confidence score falls below the threshold in getConfidenceThreshold().

Inherited Method Summary

From class java.lang.Object

Object	clone()
boolean	equals(Object arg0)
void	finalize()
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface java.io.Closeable

abstract void

close()

From interface java.lang.AutoCloseable

abstract void

close()

Constants

public static final float DEFAULT_IDENTIFY_LANGUAGE_CONFIDENCE_THRESHOLD

The default confidence threshold for the identifyLanguage(String) call.

Constant Value: 0.5

public static final float DEFAULT_IDENTIFY_POSSIBLE_LANGUAGES_CONFIDENCE_THRESHOLD

The default confidence threshold for the identifyPossibleLanguages(String) call.

Constant Value: 0.01

public static final String UNDETERMINED_LANGUAGE_CODE

The BCP-47 code for "undetermined language"

Constant Value: "und"

Public Methods

public void close ()

Releases resources when the client is finished using the instance.

The instance can still be used after a call to this method, but might take slightly longer to produce a result, because it will have to load the model again.

public Task<String> identifyLanguage (String text)

Identifies the language in a supplied String and returns the most likely language.

Parameters

text	The text for which to identify the language. Inputs longer than 200 characters are truncated to 200 characters, as longer input does not improve the detection accuracy.

Returns

• A Task that returns a String with the BCP-47 language code of the most likely language, or UNDETERMINED_LANGUAGE_CODE if the confidence was below the threshold of 0.5.

public Task<List<IdentifiedLanguage>> identifyPossibleLanguages (String text)

Identifies the language in a supplied String and returns a list of possible languages, cutting off any languages whose confidence score falls below the threshold in getConfidenceThreshold().

Note that this API assumes the text is in a single language; the returned list contains all estimations for what that language could be, along with a confidence score for each possible language. The API does not detect multiple languages in a single text.

Parameters

text	The text for which to identify the language. Inputs longer than 200 characters are truncated to 200 characters, as longer input does not improve the detection accuracy.

Returns

• A Task that returns a List of IdentifiedLanguages. The returned list will never be empty; if all languages have lower confidence scores than the threshold, the list will contain a single item with the UNDETERMINED_LANGUAGE_CODE.