Train the neural dependency parser. @param parser (Parser): Neural Dependency Parser @param train_data (): @param dev_data (): @para

Train the NMT Model. @param args (Dict): args from cmd line

Train the NMT Model. @param args (Dict): args from cmd line

Train the neural dependency parser for single epoch. Note: In PyTorch we can signify train versus test and automatically have the Dropout La

Convert list of words or list of sentences of words into list of list of indices. @param sents (list[str] or list[list[str]]): senten

Convert list of words or list of sentences of words into list or list of list of indices. @param sents (list[str] or list[list[str]])

Check if word is captured by VocabEntry. @param word (str): word to look up @returns contains (bool): whether word is contained

Check if word is captured by VocabEntry. @param word (str): word to look up @returns contains (bool): whether word is contained

Retrieve word's index. Return the index for the unk token if the word is out of vocabulary. @param word (str): word to look up.

Retrieve word's index. Return the index for the unk token if the word is out of vocabulary. @param word (str): word to look up.

Initialize the parser model. @param embeddings (Tensor): word embeddings (num_words, embedding_size) @param n_features (int): number

Initializes this partial parse. @param sentence (list of str): The sentence to be parsed as a list of words.

Apply the output of the convolution later (x_conv) through a highway network @param D_in (int): Size of input layer

Init Character Decoder. @param hidden_size (int): Hidden size of the decoder LSTM @param char_embedding_size (int): dimensionality o

Init NMT Model. @param embed_size (int): Embedding size (dimensionality) @param hidden_size (int): Hidden Size (dimensionality)

Apply the output of the convolution later (x_conv) through a highway network @param D_in (int): Size of input layer

Init VocabEntry Instance. @param word2id (dict): dictionary mapping words 2 indices

Init Vocab. @param src_vocab (VocabEntry): VocabEntry for source language @param tgt_vocab (VocabEntry): VocabEntry for target langua

Init the Embedding layer for one language @param embed_size (int): Embedding size (dimensionality) for the output @param voc

Init NMT Model. @param embed_size (int): Embedding size (dimensionality) @param hidden_size (int): Hidden Size (dimensionality)

Init VocabEntry Instance. @param word2id (dict): dictionary mapping words 2 indices

Init Vocab. @param src_vocab (VocabEntry): VocabEntry for source language @param tgt_vocab (VocabEntry): VocabEntry for target langua

Init the Embedding layers. @param embed_size (int): Embedding size (dimensionality) @param vocab (Vocab): Vocabulary object

Compute number of words in VocabEntry. @returns len (int): number of words in VocabEntry

Compute number of words in VocabEntry. @returns len (int): number of words in VocabEntry

Representation of VocabEntry to be used when printing the object.

Representation of Vocab to be used when printing the object.

Representation of VocabEntry to be used when printing the object.

Representation of Vocab to be used when printing the object.

Raise error, if one tries to edit the VocabEntry.

Raise error, if one tries to edit the VocabEntry.

Run the model forward. Note that we will not apply the softmax function here because it is included in the loss function nn.CrossEntropy

Take a mini-batch of source and target sentences, compute the log-likelihood of target sentences under the language models learned by the NMT

Looks up character-based CNN embeddings for the words in a batch of sentences. @param input: Tensor of integers of shape (sentence_le

Take a mini-batch of source and target sentences, compute the log-likelihood of target sentences under the language models learned by the NMT

Generate outputs.

Return mapping of index to word. @param wid (int): word index @returns word (str): word corresponding to index

Return mapping of index to word. @param wid (int): word index @returns word (str): word corresponding to index

Convert list of indices into words. @param word_ids (list[int]): list of word ids @return sents (list[str]): list of words

Convert list of indices into words. @param word_ids (list[int]): list of word ids @return sents (list[str]): list of words

Load the model from a file. @param model_path (str): path to model

Load the model from a file. @param model_path (str): path to model

Naive Softmax loss & gradient function for word2vec models Implement the naive softmax loss and gradients between a center word's embedding

Negative sampling loss function for word2vec models Implement the negative sampling loss and gradients for a centerWordVec and a outsideWord