Package org.tribuo.util.tokens.impl.wordpiece

Class WordpieceTokenizer

java.lang.Object
org.tribuo.util.tokens.impl.wordpiece.WordpieceTokenizer
All Implemented Interfaces:
com.oracle.labs.mlrg.olcut.config.Configurable, com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>, Cloneable, Tokenizer
public class WordpieceTokenizer extends Object implements Tokenizer
This Tokenizer is meant to be a reasonable approximation of the BertTokenizer defined here. Please see class definition for BertTokenizer (the line numbers may change.) Please see notes in WordpieceTokenizerTest for information about how we tested the similarity between this tokenizer and the referenced python implementation and for regression test examples that fail. In short, there are outstanding discrepancies for texts that include Arabic and other non-latin scripts that generate so many "[UNK]" tokens for an English-based BPE vocabulary as to render the discrepancies as practically meaningless.

As in the reference implementation, the input text is whitespace tokenized and each token is further tokenized to account for things like punctuation and Chinese characters. The resulting tokens are then applied to the wordpiece algorithm implemented in Wordpiece which is driven by an input vocabulary which matches tokens and token suffixes as it can. Any tokens that are not found in the input vocbulary are marked as "unknown".

  • Constructor Summary

    Constructors
    Constructor
    Description
    WordpieceTokenizer(Wordpiece wordpiece, Tokenizer tokenizer, boolean toLowerCase, boolean stripAccents, Set<String> neverSplit)
    Constructs a wordpiece tokenizer.

  • Method Summary

    Modifier and Type
    Method
    Description
    boolean
    advance()
    Advances the tokenizer to the next token.
    WordpieceTokenizer
    clone()
    Clones a tokenizer with it's configuration.
    int
    getEnd()
    Gets the ending offset (exclusive) of the current token in the character sequence
    com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance
    getProvenance()
     
    int
    getStart()
    Gets the starting character offset of the current token in the character sequence
    String
    getText()
    Gets the text of the current token, as a string
    Token
    getToken()
    Generates a Token object from the current state of the tokenizer.
    Token.TokenType
    getType()
    Gets the type of the current token.
    void
    reset(CharSequence cs)
    Resets the tokenizer so that it operates on a new sequence of characters.

    Methods inherited from class java.lang.Object

    equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

    Methods inherited from interface com.oracle.labs.mlrg.olcut.config.Configurable

    postConfig

    Methods inherited from interface org.tribuo.util.tokens.Tokenizer

    split, tokenize

  • Constructor Details

    • WordpieceTokenizer

      public WordpieceTokenizer(Wordpiece wordpiece, Tokenizer tokenizer, boolean toLowerCase, boolean stripAccents, Set<String> neverSplit)
      Constructs a wordpiece tokenizer.
      Parameters:
      wordpiece - an instance of Wordpiece
      tokenizer - Wordpiece is run on the tokens generated by the tokenizer provided here.
      toLowerCase - determines whether or not to lowercase each token before running Wordpiece on it
      stripAccents - determines whether or not to strip out accents from each token before running Wordpiece on it
      neverSplit - a set of token values that we will not apply Wordpiece to.

  • Method Details

    • getProvenance

      public com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance getProvenance()
      Specified by:
      getProvenance in interface com.oracle.labs.mlrg.olcut.provenance.Provenancable<com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance>

    • reset

      public void reset(CharSequence cs)
      Description copied from interface: Tokenizer
      Resets the tokenizer so that it operates on a new sequence of characters.
      Specified by:
      reset in interface Tokenizer
      Parameters:
      cs - a character sequence to tokenize

    • advance

      public boolean advance()
      Description copied from interface: Tokenizer
      Advances the tokenizer to the next token.
      Specified by:
      advance in interface Tokenizer
      Returns:
      true if there is such a token, false otherwise.

    • getToken

      public Token getToken()
      Description copied from interface: Tokenizer
      Generates a Token object from the current state of the tokenizer.
      Specified by:
      getToken in interface Tokenizer
      Returns:
      The token object from the current state.

    • getText

      public String getText()
      Description copied from interface: Tokenizer
      Gets the text of the current token, as a string
      Specified by:
      getText in interface Tokenizer
      Returns:
      the text of the current token

    • getStart

      public int getStart()
      Description copied from interface: Tokenizer
      Gets the starting character offset of the current token in the character sequence
      Specified by:
      getStart in interface Tokenizer
      Returns:
      the starting character offset of the token

    • getEnd

      public int getEnd()
      Description copied from interface: Tokenizer
      Gets the ending offset (exclusive) of the current token in the character sequence
      Specified by:
      getEnd in interface Tokenizer
      Returns:
      the exclusive ending character offset for the current token.

    • getType

      public Token.TokenType getType()
      Description copied from interface: Tokenizer
      Gets the type of the current token.
      Specified by:
      getType in interface Tokenizer
      Returns:
      the type of the current token.

    • clone

      public WordpieceTokenizer clone()
      Description copied from interface: Tokenizer
      Clones a tokenizer with it's configuration. Cloned tokenizers are not processing the same text as the original tokenizer and need to be reset with a fresh CharSequence.
      Specified by:
      clone in interface Tokenizer
      Overrides:
      clone in class Object
      Returns:
      A tokenizer with the same configuration, but independent state.