nlp_architect.models.matchlstm_ansptr.MatchLSTMAnswerPointer

class nlp_architect.models.matchlstm_ansptr.MatchLSTMAnswerPointer(params_dict, embeddings)

Defines end to end MatchLSTM and Answer_Pointer network for Reading Comprehension

__init__(params_dict, embeddings)

Parameters:

• params_dict – Dictionary containing the following keys- ‘max_question’ : max length of all questions in the dataset ‘max_para’ : max length of all paragraphs in the dataset ‘hidden_size’: number of hidden units in the network ‘batch_size’ : batch size defined by user
• embeddings – Glove pretrained embedding matrix

Methods

__init__(params_dict, embeddings)	param params_dict:  Dictionary containing the following keys-
answer_pointer_pass()	Function to run the answer pointer pass:
cal_f1_score(ground_truths, predictions)	Function to calculate F-1 and EM scores
create_model()	Function to set up the end 2 end reading comprehension model
create_variables()	Function to create variables used for training
get_dynamic_feed_params(question_str, …)	Function to get required feed_dict format for user entered questions.
inference_mode(session, valid, vocab_tuple, …)	Function to run inference_mode for reading comprehension
obtain_indices(preds_start, preds_end)	Function to get answer indices given the predictions
run_loop(session, train[, mode, dropout])	Function to run training/validation loop and display training loss, F1 & EM scores
unroll_with_attention([reverse])	Function to run the match_lstm pass in both forward and reverse directions

answer_pointer_pass()

Function to run the answer pointer pass:

Parameters:None – Returns:List of logits for start and end indices of the answer

cal_f1_score(ground_truths, predictions)

Function to calculate F-1 and EM scores

Parameters:

• ground_truths – labels given in the dataset
• predictions – logits predicted by the network

Returns:

F1 score and Exact-Match score

create_model()

Function to set up the end 2 end reading comprehension model

create_variables()

Function to create variables used for training

get_dynamic_feed_params(question_str, vocab_reverse)

Function to get required feed_dict format for user entered questions. Used mainly in the demo mode.

Parameters:

• question_str – question string
• vocab_reverse – vocab dictionary with words as keys and indices as values

Returns:

list of indicies represnting the question padded to max length question_len: actual length of the question ques_mask: mask for question_idx

Return type:

question_idx

inference_mode(session, valid, vocab_tuple, num_examples, dropout=1.0, dynamic_question_mode=False, dynamic_usr_question='', dynamic_question_index=0)

Function to run inference_mode for reading comprehension

Parameters:

• session – tensorflow session
• valid – data dictionary for validation set
• vocab_tuple – a tuple containing voacab dictionaries in forward and reverse directions
• num_examples – specify the number of samples to run for inference
• dropout – Float value which is always 1.0 for inference
• dynamic_question_mode – boolean to enable whether or not accept questions from the user(used in the demo mode)

static obtain_indices(preds_start, preds_end)

Function to get answer indices given the predictions

Parameters:

• preds_start – predicted start indices
• predictions – predicted end indices

Returns:

final start and end indices for the answer

run_loop(session, train, mode='train', dropout=0.6)

Function to run training/validation loop and display training loss, F1 & EM scores

Parameters:

• session – tensorflow session
• train – data dictionary for training/validation
• dropout – float value
• mode – ‘train’/’val’

unroll_with_attention(reverse=False)

Function to run the match_lstm pass in both forward and reverse directions

Args: reverse: Boolean indicating whether to unroll in reverse directions