Python data.article2ids() Examples

The following are 6 code examples of data.article2ids(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module data , or try the search function .
Example #1
Source File: batcher.py    From Reinforce-Paraphrase-Generation with MIT License 5 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab):
    # Get ids of special tokens
    start_decoding = vocab.word2id(data.START_DECODING)
    stop_decoding = vocab.word2id(data.STOP_DECODING)

    # Process the article
    article_words = article.split()
    if len(article_words) > config.max_enc_steps:
      article_words = article_words[:config.max_enc_steps]
    self.enc_len = len(article_words) # store the length after truncation but before padding
    self.enc_input = [vocab.word2id(w) for w in article_words] # list of word ids; OOVs are represented by the id for UNK token
    
    # Process the abstract
    abstract = ' '.join(abstract_sentences)
    abstract_words = abstract.split() # list of strings
    abs_ids = [vocab.word2id(w) for w in abstract_words] # list of word ids; OOVs are represented by the id for UNK token
    
    # Get the decoder input sequence and target sequence
    self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, config.max_dec_steps, start_decoding, stop_decoding)
    self.dec_len = len(self.dec_input)

    # If using pointer-generator mode, we need to store some extra info
    if config.pointer_gen:
      # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
      self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

      # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
      abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

      # Overwrite decoder target sequence so it uses the temp article OOV ids
      # NOTE: dec_input does not contain article OOV ids!!!!
      _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, config.max_dec_steps, start_decoding, stop_decoding)

    # Store the original strings
    self.original_article = article
    self.original_abstract = abstract
    self.original_abstract_sents = abstract_sentences
Example #2
Source File: batcher.py    From pointer_summarizer with Apache License 2.0 5 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab):
    # Get ids of special tokens
    start_decoding = vocab.word2id(data.START_DECODING)
    stop_decoding = vocab.word2id(data.STOP_DECODING)

    # Process the article
    article_words = article.split()
    if len(article_words) > config.max_enc_steps:
      article_words = article_words[:config.max_enc_steps]
    self.enc_len = len(article_words) # store the length after truncation but before padding
    self.enc_input = [vocab.word2id(w) for w in article_words] # list of word ids; OOVs are represented by the id for UNK token

    # Process the abstract
    abstract = ' '.join(abstract_sentences) # string
    abstract_words = abstract.split() # list of strings
    abs_ids = [vocab.word2id(w) for w in abstract_words] # list of word ids; OOVs are represented by the id for UNK token

    # Get the decoder input sequence and target sequence
    self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, config.max_dec_steps, start_decoding, stop_decoding)
    self.dec_len = len(self.dec_input)

    # If using pointer-generator mode, we need to store some extra info
    if config.pointer_gen:
      # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
      self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

      # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
      abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

      # Overwrite decoder target sequence so it uses the temp article OOV ids
      _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, config.max_dec_steps, start_decoding, stop_decoding)

    # Store the original strings
    self.original_article = article
    self.original_abstract = abstract
    self.original_abstract_sents = abstract_sentences
Example #3
Source File: batcher.py    From TransferRL with MIT License 4 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab, hps):
    """Initializes the Example, performing tokenization and truncation to produce the encoder, decoder and target sequences, which are stored in self.

    Args:
      article: source text; a string. each token is separated by a single space.
      abstract_sentences: list of strings, one per abstract sentence. In each sentence, each token is separated by a single space.
      vocab: Vocabulary object
      hps: hyperparameters
    """
    self.hps = hps

    # Get ids of special tokens
    start_decoding = vocab.word2id(data.START_DECODING)
    stop_decoding = vocab.word2id(data.STOP_DECODING)

    # Process the article
    article_words = article.split()
    if len(article_words) > hps.max_enc_steps:
      article_words = article_words[:hps.max_enc_steps]
    self.enc_len = len(article_words) # store the length after truncation but before padding
    self.enc_input = [vocab.word2id(w) for w in article_words] # list of word ids; OOVs are represented by the id for UNK token

    # Process the abstract
    abstract = ' '.join(abstract_sentences) # string
    abstract_words = abstract.split() # list of strings
    abs_ids = [vocab.word2id(w) for w in abstract_words] # list of word ids; OOVs are represented by the id for UNK token

    # Get the decoder input sequence and target sequence
    self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, hps.max_dec_steps, start_decoding, stop_decoding)
    self.dec_len = len(self.dec_input)

    # If using pointer-generator mode, we need to store some extra info
    if hps.pointer_gen:
      # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
      self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

      # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
      abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

      # Overwrite decoder target sequence so it uses the temp article OOV ids
      _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, hps.max_dec_steps, start_decoding, stop_decoding)

    # Store the original strings
    self.original_article = article
    self.original_abstract = abstract
    self.original_abstract_sents = abstract_sentences
Example #4
Source File: batcher.py    From RLSeq2Seq with MIT License 4 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab, hps):
    """Initializes the Example, performing tokenization and truncation to produce the encoder, decoder and target sequences, which are stored in self.

    Args:
      article: source text; a string. each token is separated by a single space.
      abstract_sentences: list of strings, one per abstract sentence. In each sentence, each token is separated by a single space.
      vocab: Vocabulary object
      hps: hyperparameters
    """
    self.hps = hps

    # Get ids of special tokens
    start_decoding = vocab.word2id(data.START_DECODING)
    stop_decoding = vocab.word2id(data.STOP_DECODING)

    # Process the article
    article_words = article.split()
    if len(article_words) > hps.max_enc_steps:
      article_words = article_words[:hps.max_enc_steps]
    self.enc_len = len(article_words) # store the length after truncation but before padding
    self.enc_input = [vocab.word2id(w) for w in article_words] # list of word ids; OOVs are represented by the id for UNK token

    # Process the abstract
    abstract = ' '.join(abstract_sentences) # string
    abstract_words = abstract.split() # list of strings
    abs_ids = [vocab.word2id(w) for w in abstract_words] # list of word ids; OOVs are represented by the id for UNK token

    # Get the decoder input sequence and target sequence
    self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, hps.max_dec_steps, start_decoding, stop_decoding)
    self.dec_len = len(self.dec_input)

    # If using pointer-generator mode, we need to store some extra info
    if hps.pointer_gen:
      # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
      self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

      # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
      abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

      # Overwrite decoder target sequence so it uses the temp article OOV ids
      _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, hps.max_dec_steps, start_decoding, stop_decoding)

    # Store the original strings
    self.original_article = article
    self.original_abstract = abstract
    self.original_abstract_sents = abstract_sentences
Example #5
Source File: batcher.py    From MAX-Text-Summarizer with Apache License 2.0 4 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab, hps):
        """Initializes the Example, performing tokenization and truncation to produce the encoder, decoder and target sequences, which are stored in self.

    Args:
      article: source text; a string. each token is separated by a single space.
      abstract_sentences: list of strings, one per abstract sentence. In each sentence, each token is separated by a single space.
      vocab: Vocabulary object
      hps: hyperparameters
    """
        self.hps = hps

        # Get ids of special tokens
        start_decoding = vocab.word2id(data.START_DECODING)
        stop_decoding = vocab.word2id(data.STOP_DECODING)

        # Process the article
        article_words = article.split()
        if len(article_words) > hps.max_enc_steps:
            article_words = article_words[:hps.max_enc_steps]
        self.enc_len = len(article_words)  # store the length after truncation but before padding
        self.enc_input = [vocab.word2id(w) for w in
                          article_words]  # list of word ids; OOVs are represented by the id for UNK token

        # Process the abstract
        abstract = ' '.join(abstract_sentences)  # string
        abstract_words = abstract.split()  # list of strings
        abs_ids = [vocab.word2id(w) for w in
                   abstract_words]  # list of word ids; OOVs are represented by the id for UNK token

        # Get the decoder input sequence and target sequence
        self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, hps.max_dec_steps, start_decoding,
                                                                 stop_decoding)
        self.dec_len = len(self.dec_input)

        # If using pointer-generator mode, we need to store some extra info
        if hps.pointer_gen:
            # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
            self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

            # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
            abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

            # Overwrite decoder target sequence so it uses the temp article OOV ids
            _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, hps.max_dec_steps, start_decoding,
                                                        stop_decoding)

        # Store the original strings
        self.original_article = article
        self.original_abstract = abstract
        self.original_abstract_sents = abstract_sentences
Example #6
Source File: batcher.py    From pointer-generator with Apache License 2.0 4 votes vote down vote up 
def __init__(self, article, abstract_sentences, vocab, hps):
    """Initializes the Example, performing tokenization and truncation to produce the encoder, decoder and target sequences, which are stored in self.

    Args:
      article: source text; a string. each token is separated by a single space.
      abstract_sentences: list of strings, one per abstract sentence. In each sentence, each token is separated by a single space.
      vocab: Vocabulary object
      hps: hyperparameters
    """
    self.hps = hps

    # Get ids of special tokens
    start_decoding = vocab.word2id(data.START_DECODING)
    stop_decoding = vocab.word2id(data.STOP_DECODING)

    # Process the article
    article_words = article.split()
    if len(article_words) > hps.max_enc_steps:
      article_words = article_words[:hps.max_enc_steps]
    self.enc_len = len(article_words) # store the length after truncation but before padding
    self.enc_input = [vocab.word2id(w) for w in article_words] # list of word ids; OOVs are represented by the id for UNK token

    # Process the abstract
    abstract = ' '.join(abstract_sentences) # string
    abstract_words = abstract.split() # list of strings
    abs_ids = [vocab.word2id(w) for w in abstract_words] # list of word ids; OOVs are represented by the id for UNK token

    # Get the decoder input sequence and target sequence
    self.dec_input, self.target = self.get_dec_inp_targ_seqs(abs_ids, hps.max_dec_steps, start_decoding, stop_decoding)
    self.dec_len = len(self.dec_input)

    # If using pointer-generator mode, we need to store some extra info
    if hps.pointer_gen:
      # Store a version of the enc_input where in-article OOVs are represented by their temporary OOV id; also store the in-article OOVs words themselves
      self.enc_input_extend_vocab, self.article_oovs = data.article2ids(article_words, vocab)

      # Get a verison of the reference summary where in-article OOVs are represented by their temporary article OOV id
      abs_ids_extend_vocab = data.abstract2ids(abstract_words, vocab, self.article_oovs)

      # Overwrite decoder target sequence so it uses the temp article OOV ids
      _, self.target = self.get_dec_inp_targ_seqs(abs_ids_extend_vocab, hps.max_dec_steps, start_decoding, stop_decoding)

    # Store the original strings
    self.original_article = article
    self.original_abstract = abstract
    self.original_abstract_sents = abstract_sentences