TensorflowRoBerta

The RoBERTa model was proposed in RoBERTa: A Robustly Optimized BERT Pretraining Approach https://arxiv.org/abs/1907.11692> by Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov. It is based on Google's BERT model released in 2018.

It builds on BERT and modifies key hyperparameters, removing the next-sentence pretraining objective and training with much larger mini-batches and learning rates. The abstract from the paper is the following:

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.*

Tips:

- RoBERTa has the same architecture as BERT, but uses a byte-level BPE as a tokenizer (same as GPT-2) and uses a different pretraining scheme.

- RoBERTa doesn't have :obj:token_type_ids, you don't need to indicate which token belongs to which segment. Just separate your segments with the separation token :obj:tokenizer.sep_token (or :obj:</s>)

The original code can be found here https://github.com/pytorch/fairseq/tree/master/examples/roberta.

Linear Supertypes

Serializable, Serializable, AnyRef, Any

Instance Constructors

new TensorflowRoBerta(tensorflowWrapper: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, padTokenId: Int, configProtoBytes: Option[Array[Byte]] = None, signatures: Option[Map[String, String]] = None)

tensorflowWrapper
tensorflowWrapper class
sentenceStartTokenId
special token id for <s>
sentenceEndTokenId
special token id for </s>
configProtoBytes
ProtoBytes for TensorFlow session config
signatures
Model's inputs and output(s) signatures

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
val _tfRoBertaSignatures: Map[String, String]
final def asInstanceOf[T0]: T0

Definition Classes
Any
def calculateEmbeddings(sentences: Seq[WordpieceTokenizedSentence], originalTokenSentences: Seq[TokenizedSentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean): Seq[WordpieceEmbeddingsSentence]
def calculateSentenceEmbeddings(tokens: Seq[WordpieceTokenizedSentence], sentences: Seq[Sentence], batchSize: Int, maxSentenceLength: Int): Seq[Annotation]
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def encode(sentences: Seq[(WordpieceTokenizedSentence, Int)], maxSequenceLength: Int): Seq[Array[Int]]

Encode the input sequence to indexes IDs adding padding where necessary
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
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def tag(batch: Seq[Array[Int]]): Seq[Array[Array[Float]]]
def tagSentence(batch: Seq[Array[Int]]): Array[Array[Float]]

batch
batches of sentences
returns
batches of vectors for each sentence
val tensorflowWrapper: TensorflowWrapper

tensorflowWrapper class
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 Doc: package tensorflow

class TensorflowRoBerta extends Serializable

Instance Constructors

new TensorflowRoBerta(tensorflowWrapper: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, padTokenId: Int, configProtoBytes: Option[Array[Byte]] = None, signatures: Option[Map[String, String]] = None)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

val _tfRoBertaSignatures: Map[String, String]

final def asInstanceOf[T0]: T0

def calculateEmbeddings(sentences: Seq[WordpieceTokenizedSentence], originalTokenSentences: Seq[TokenizedSentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean): Seq[WordpieceEmbeddingsSentence]

def calculateSentenceEmbeddings(tokens: Seq[WordpieceTokenizedSentence], sentences: Seq[Sentence], batchSize: Int, maxSentenceLength: Int): Seq[Annotation]

def clone(): AnyRef

def encode(sentences: Seq[(WordpieceTokenizedSentence, Int)], maxSequenceLength: Int): Seq[Array[Int]]

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

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

def tag(batch: Seq[Array[Int]]): Seq[Array[Array[Float]]]

def tagSentence(batch: Seq[Array[Int]]): Array[Array[Float]]

val tensorflowWrapper: TensorflowWrapper

def toString(): String

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped