Load vocabulary from JSON dump. @param file_path (str): file path to vocab file @returns Vocab object loaded from JSON dump

Load vocabulary from JSON dump. @param file_path (str): file path to vocab file @returns Vocab object loaded from JSON dump

Read file, where each sentence is dilineated by a `\n`. @param file_path (str): path to file containing corpus @param source (str): "tgt" or

Read file, where each sentence is dilineated by a `\n`. @param file_path (str): path to file containing corpus @param source (str): "tgt" or

Save Vocab to file as JSON dump. @param file_path (str): file path to vocab file

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

Convert list of sentences (words) into tensor with necessary padding for shorter sentences. @param sents (List[List[str]]): list of

Convert list of sentences (words) into tensor with necessary padding for shorter sentences. @param sents (List[List[str]]): list of

Compute one forward step of the LSTM decoder, including the attention computation. @param Ybar_t (Tensor): Concatenated Tensor of [Y_t o_pre

Apply the encoder to source sentences to obtain encoder hidden states. Additionally, take the final states of the encoder and project the

Reinitialize the Layer Weights for Sanity Checks.

Stochastic Gradient Descent Implement the stochastic gradient descent method in this function. Arguments: f -- the function to optimize

Tests the provided dependencies match the expected dependencies

Yield batches of source and target sentences reverse sorted by length (largest to smallest). @param data (list of (src_sent, tgt_sent)): list of

Compute combined output vectors for a batch. @param enc_hiddens (Tensor): Hidden states (b, src_len, h*2), where

Apply the output of the convolution later (x_conv) through a highway network @param x (Tensor): Input x_cov gets applied to

Performs a single parse step by applying the given transition to this partial parse @param transition (str): A string that equals "S", "LA",

Compute one forward step of the LSTM decoder, including the attention computation. @param Ybar_t (Tensor): Concatenated Tensor of [Y_t o_prev

Tests that a single parse step returns the expected output

Yield batches of source and target sentences reverse sorted by length (largest to smallest). @param data (list of (src_sent, tgt_sent)): list of

Greedy decoding @param initialStates: initial internal state of the LSTM, a tuple of two tensors of size (1, batch, hidden_size) @par

Determine which device to place the Tensors upon, CPU or GPU.

Determine which device to place the Tensors upon, CPU or GPU.

Apply the encoder to source sentences to obtain encoder hidden states. Additionally, take the final states of the encoder and project the

Given a corpus construct a Vocab Entry. @param corpus (list[str]): corpus of text produced by read_corpus function @param size (int):

Given a corpus construct a Vocab Entry. @param corpus (list[str]): corpus of text produced by read_corpus function @param size (int):

Generate sentence masks for encoder hidden states. @param enc_hiddens (Tensor): encodings of shape (b, src_len, 2*h), where b = batch size,

Parses a list of sentences in minibatches using a model. @param sentences (list of list of str): A list of sentences to be parsed

Pad list of sentences according to the longest sentence in the batch and max_word_length. @param sents (list[list[list[int]]]): list of sentences

Save Vocab to file as JSON dump. @param file_path (str): file path to vocab file

Compute the sigmoid function for the input here. Arguments: x -- A scalar or numpy array. Return: s -- sigmoid(x)

Skip-gram model in word2vec Implement the skip-gram model in this function. Arguments: currentCenterWord -- a string of the current cen

Forward computation during training. @param char_sequence: tensor of integers, shape (length, batch). Note that "length" here and in forward

Add word to VocabEntry, if it is previously unseen. @param word (str): word to add to VocabEntry @return index (int): index that the

Add word to VocabEntry, if it is previously unseen. @param word (str): word to add to VocabEntry @return index (int): index that the

Run beam search to construct hypotheses for a list of src-language sentences. @param model (NMT): NMT Model @param test_data_src (List[List[s

Run beam search to construct hypotheses for a list of src-language sentences. @param model (NMT): NMT Model @param test_data_src (List[List[s

Given a single source sentence, perform beam search, yielding translations in the target language. @param src_sent (List[str]): a single sour

Given a single source sentence, perform beam search, yielding translations in the target language. @param src_sent (List[str]): a single sour

Build Vocabulary. @param src_sents (list[str]): Source sentences provided by read_corpus() function @param tgt_sents (list[str]): Tar

Build Vocabulary. @param src_sents (list[str]): Source sentences provided by read_corpus() function @param tgt_sents (list[str]): Tar

Given decoding results and reference sentences, compute corpus-level BLEU score. @param references (List[List[str]]): a list of gold-standard ref

Given decoding results and reference sentences, compute corpus-level BLEU score. @param references (List[List[str]]): a list of gold-standard ref

Performs decoding on a test set, and save the best-scoring decoding results. If the target gold-standard sentences are given, the function also c

Performs decoding on a test set, and save the best-scoring decoding results. If the target gold-standard sentences are given, the function also c

Compute combined output vectors for a batch. @param enc_hiddens (Tensor): Hidden states (b, src_len, h*2), where

Utilize `self.pretrained_embeddings` to map input `t` from input tokens (integers) to embedding vectors. PyTorch Notes:

Evaluate perplexity on dev sentences @param model (NMT): NMT Model @param dev_data (list of (src_sent, tgt_sent)): list of tuples containing

Evaluate perplexity on dev sentences @param model (NMT): NMT Model @param dev_data (list of (src_sent, tgt_sent)): list of tuples containing

Forward pass of character decoder. @param input: tensor of integers, shape (length, batch) @param dec_hidden: internal state of the

Apply the output of the convolution later (x_conv) through a highway network @param x (Tensor): Input x_cov gets applied to

Generate sentence masks for encoder hidden states. @param enc_hiddens (Tensor): encodings of shape (b, src_len, 2*h), where b = batch size,

Samples K indexes which are not the outsideWordIdx

Iterates through the provided data one minibatch at at time. You can use this function to iterate through data in minibatches as follows:

A helper function that loads previously saved parameters and resets iteration start.

Main func.

Main func.

Main func.

Main func.

Pad list of sentences according to the longest sentence in the batch. @param sents (list[list[int]]): list of sentences, where each sentence

Pad list of sentences according to the longest sentence in the batch. @param sents (list[list[str]]): list of sentences, where each sentence

Applies the provided transitions to this PartialParse @param transitions (list of str): The list of transitions in the order they should be a

Sanity check for question 1d. Compares student output to that of model with dummy data.

Sanity check for words2charindices function.

Sanity check for question 1e. Compares student output to that of model with dummy data.

Sanity check for pad_sents_char() function.

Sanity check for question 1f. Compares student output to that of model with dummy data.

Sanity check for pad_sents_char() function.

Sanity check for highway network

Sanity check for highway network

Sanity check for model_embeddings.py basic shape check

Sanity check for CharDecoder.__init__() basic shape check

Sanity check for CharDecoder.forward() basic shape check

Sanity check for CharDecoder.train_forward() basic shape check

Sanity check for CharDecoder.decode_greedy() basic shape check

Save the odel to a file. @param path (str): path to the model

Save the odel to a file. @param path (str): path to the model

Simple tests for the minibatch_parse function Warning: these are not exhaustive

Simple tests for the PartialParse.parse function Warning: these are not exhaustive

Simple tests for the PartialParse.parse_step function Warning: these are not exhaustive

Test the two word2vec implementations, before running on Stanford Sentiment Treebank

Convert list of sentences (words) into tensor with necessary padding for shorter sentences. @param sents (List[List[str]]): list of