:param x1: [batch_size,story_length,hidden_size] :param x2: [batch_size,1,hidden_size] :param scope: a string :re

Performs invalid character removal and whitespace cleanup on text.

Decodes a record to a TensorFlow example.

Whether to use L2 weight decay for `param_name`.

Get the variable name from the tensor name.

Checks whether CP is the codepoint of a CJK character.

Checks whether `chars` is a control character.

Checks whether `chars` is a punctuation character.

Checks whether `chars` is a whitespace character.

Splits punctuation on a piece of text.

Strips accents from a piece of text.

Adds whitespace around any CJK character.

Truncates a sequence pair in place to the maximum length.

Truncates a sequence pair in place to the maximum length.

Answer Module:generate an answer from the final memory vector. Input: hidden state from episodic memory module:[batch_size,hidd

Raises an exception if the tensor rank is not of the expected rank. Args: tensor: A tf.Tensor to check the rank of. expected_rank: Python i

Performs multi-headed attention from `from_tensor` to `to_tensor`. This is an implementation of multi-headed attention based on "Attention is all

parallel implemtation of gate function given a list of candidate sentence, a query, and previous memory. Input: c_full: candidat

input1: hidden_state_sentence: a list,len:num_sentence,element:[None,hidden_size*4] input2: sentence level context vector:[self.hidde

input1: hidden_state_sentence: a list,len:num_sentence,element:[None,hidden_size*4] input2: sentence level context vector:[self.hidde

input1:self.hidden_state: hidden_state:list,len:sentence_length,element:[batch_size*num_sentences,hidden_size*2] input2:sentence leve

input1:self.hidden_state: hidden_state:list,len:sentence_length,element:[batch_size*num_sentences,hidden_size*2] input2:sentence leve

parallel implementation of single time step for compute of input with memory :param s_t: [batch_size,hidden_size].vector represen

compute micro FP,FP,FN :param label_dict_accusation: a dict. {label:(TP, FP, FN)} :return:TP_micro,FP_micro,FN_micro

compute true postive(TP), false postive(FP), false negative(FN) given target lable and predict label :param target_y: :param predict_y:

compute f1_macro :param label_dict: {label:(TP,FP,FN)} :return: f1_macro

compute f1_micro :param label_dict: {label:(TP,FP,FN)} :return: f1_micro: a scalar

input:self.embedded_words:[None,sentence_length,embed_size] :return: shape:[None,sentence_length,embed_size*3]

input:self.embedded_words:[None,sentence_length,embed_size] :return: shape:[None,sentence_length,embed_size*3]

input:self.embedded_words:[None,sentence_length,embed_size] :return: shape:[None,sentence_length,embed_size*3]

Converts a single `InputExample` into a single `InputFeatures`.

Create 3D attention mask from a 2D tensor mask. Args: from_tensor: 2D or 3D Tensor of shape [batch_size, from_seq_length, ...]. to_mask: in

Creates a classification model.

Creates a classification model.

Creates a classification model.

Creates a classification model.

Creates a classification model.

evalution on model using validation data

evalution on model using validation data :param sess: :param input_ids: :param input_mask: :param segment_ids: :param label_i

Looks up words embeddings for id tensor. Args: input_ids: int32 Tensor of shape [batch_size, seq_length] containing word ids. vocab_s

Performs various post-processing on a word embedding tensor. Args: input_tensor: float Tensor of shape [batch_size, seq_length, embedding

singel layer for encoder.each layers has two sub-layers: the first is multi-head self-attention mechanism; the second is position-w

episodic memory module 1.combine features 1.attention mechansim using gate function.take fact representation c,question q,

Get a loop_function that extracts the previous symbol and embeds it. Used by decoder. :param embedding: embedding tensor for symbol :para

f1 score

Constructs a `BertConfig` from a Python dictionary of parameters.

gated gru to get updated hidden state :param c_current: [batch_size,embedding_size] :param h_previous:[batch_size,hidden

Maps a string to a Python function, e.g., "relu" => `tf.nn.relu`. Args: activation_string: String name of the activation function. Returns:

:param context_left:[batch_size,self.embed_size] :param embedding_previous:[batch_size,self.embed_size] :return: output:[None

:param context_left: :param embedding_previous: :return: output:[None,embed_size]

:param context_left: :param embedding_previous: :return: output:[None,embed_size]

:param context_right:[batch_size,self.embed_size] :param embedding_afterward:[batch_size,self.embed_size] :return: output:[ba

:param context_right: :param embedding_afterward: :return: output:[None,embed_size]

:param context_right: :param embedding_afterward: :return: output:[None,embed_size]

Gets a collection of `InputExample`s for the dev set.