class TokenClassifier extends AnyRef
Implements the inference step of a token classifier for multi-task learning The classifier uses a single encoder to generate the hidden state representation for every token and one linear classifier per task to produce task-specific token labels. Note that the encoder is The token classifier expects the model to be loaded to saved in one directory in the following format: encoder.onnx - ONNX-formatted encoder model encoder.name - Hugging Face name of the transformer used as the encoder tasks/ 0/ name - task name weights - weights of the linear classifier biases - biases of the linear classifier labels - array of labels to be predicted 1/ ... (same as task 0) 2/ ... (same as task 0) ...
- Alphabetic
- By Inheritance
- TokenClassifier
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new TokenClassifier(encoder: Encoder, maxTokens: Int, tasks: Array[LinearLayer], tokenizer: Tokenizer)
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
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @native()
- val encoder: Encoder
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable])
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- val maxTokens: Int
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- def predict(words: Seq[String], headTaskName: String = "Deps Head"): Array[Array[String]]
Predict labels for all tasks for a given sentence
Predict labels for all tasks for a given sentence
- words
Words in this sentence
- returns
Sequnce of labels for each task, for each token
- def predictWithScores(words: Seq[String], headTaskName: String = "Deps Head"): Array[Array[Array[(String, Float)]]]
Predict labels together with their scores for all tasks for a given sentence
Predict labels together with their scores for all tasks for a given sentence
- words
Words in this sentence
- headTaskName
Which tasks indicates the predictions for dependency heads (if any)
- returns
Labels and scores. Dimensions are: tasks x tokens in the sentence x array of (label, logit) per token
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- val tasks: Array[LinearLayer]
- def toString(): String
- Definition Classes
- AnyRef → Any
- val tokenizer: Tokenizer
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()