Question Generation

class augmentation.question_generator.generator.QuestionGenerator

Bases: object

Class loads pipeline for generating questions from text

static generate(text: str)

generates questions for given text

Parameters:

text – sentence or paragraph for question generation

Returns:

list of questions

model = T5ForConditionalGeneration(   (shared): Embedding(32128, 768)   (encoder): T5Stack(     (embed_tokens): Embedding(32128, 768)     (block): ModuleList(       (0): T5Block(         (layer): ModuleList(           (0): T5LayerSelfAttention(             (SelfAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)               (relative_attention_bias): Embedding(32, 12)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (1): T5LayerFF(             (DenseReluDense): T5DenseActDense(               (wi): Linear(in_features=768, out_features=3072, bias=False)               (wo): Linear(in_features=3072, out_features=768, bias=False)               (dropout): Dropout(p=0.1, inplace=False)               (act): ReLU()             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )         )       )       (1-11): 11 x T5Block(         (layer): ModuleList(           (0): T5LayerSelfAttention(             (SelfAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (1): T5LayerFF(             (DenseReluDense): T5DenseActDense(               (wi): Linear(in_features=768, out_features=3072, bias=False)               (wo): Linear(in_features=3072, out_features=768, bias=False)               (dropout): Dropout(p=0.1, inplace=False)               (act): ReLU()             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )         )       )     )     (final_layer_norm): T5LayerNorm()     (dropout): Dropout(p=0.1, inplace=False)   )   (decoder): T5Stack(     (embed_tokens): Embedding(32128, 768)     (block): ModuleList(       (0): T5Block(         (layer): ModuleList(           (0): T5LayerSelfAttention(             (SelfAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)               (relative_attention_bias): Embedding(32, 12)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (1): T5LayerCrossAttention(             (EncDecAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (2): T5LayerFF(             (DenseReluDense): T5DenseActDense(               (wi): Linear(in_features=768, out_features=3072, bias=False)               (wo): Linear(in_features=3072, out_features=768, bias=False)               (dropout): Dropout(p=0.1, inplace=False)               (act): ReLU()             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )         )       )       (1-11): 11 x T5Block(         (layer): ModuleList(           (0): T5LayerSelfAttention(             (SelfAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (1): T5LayerCrossAttention(             (EncDecAttention): T5Attention(               (q): Linear(in_features=768, out_features=768, bias=False)               (k): Linear(in_features=768, out_features=768, bias=False)               (v): Linear(in_features=768, out_features=768, bias=False)               (o): Linear(in_features=768, out_features=768, bias=False)             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )           (2): T5LayerFF(             (DenseReluDense): T5DenseActDense(               (wi): Linear(in_features=768, out_features=3072, bias=False)               (wo): Linear(in_features=3072, out_features=768, bias=False)               (dropout): Dropout(p=0.1, inplace=False)               (act): ReLU()             )             (layer_norm): T5LayerNorm()             (dropout): Dropout(p=0.1, inplace=False)           )         )       )     )     (final_layer_norm): T5LayerNorm()     (dropout): Dropout(p=0.1, inplace=False)   )   (lm_head): Linear(in_features=768, out_features=32128, bias=False) )

tokenizer = T5TokenizerFast(name_or_path='mrm8488/t5-base-e2e-question-generation', vocab_size=32100, model_max_length=512, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>', 'additional_special_tokens': ['<extra_id_0>', '<extra_id_1>', '<extra_id_2>', '<extra_id_3>', '<extra_id_4>', '<extra_id_5>', '<extra_id_6>', '<extra_id_7>', '<extra_id_8>', '<extra_id_9>', '<extra_id_10>', '<extra_id_11>', '<extra_id_12>', '<extra_id_13>', '<extra_id_14>', '<extra_id_15>', '<extra_id_16>', '<extra_id_17>', '<extra_id_18>', '<extra_id_19>', '<extra_id_20>', '<extra_id_21>', '<extra_id_22>', '<extra_id_23>', '<extra_id_24>', '<extra_id_25>', '<extra_id_26>', '<extra_id_27>', '<extra_id_28>', '<extra_id_29>', '<extra_id_30>', '<extra_id_31>', '<extra_id_32>', '<extra_id_33>', '<extra_id_34>', '<extra_id_35>', '<extra_id_36>', '<extra_id_37>', '<extra_id_38>', '<extra_id_39>', '<extra_id_40>', '<extra_id_41>', '<extra_id_42>', '<extra_id_43>', '<extra_id_44>', '<extra_id_45>', '<extra_id_46>', '<extra_id_47>', '<extra_id_48>', '<extra_id_49>', '<extra_id_50>', '<extra_id_51>', '<extra_id_52>', '<extra_id_53>', '<extra_id_54>', '<extra_id_55>', '<extra_id_56>', '<extra_id_57>', '<extra_id_58>', '<extra_id_59>', '<extra_id_60>', '<extra_id_61>', '<extra_id_62>', '<extra_id_63>', '<extra_id_64>', '<extra_id_65>', '<extra_id_66>', '<extra_id_67>', '<extra_id_68>', '<extra_id_69>', '<extra_id_70>', '<extra_id_71>', '<extra_id_72>', '<extra_id_73>', '<extra_id_74>', '<extra_id_75>', '<extra_id_76>', '<extra_id_77>', '<extra_id_78>', '<extra_id_79>', '<extra_id_80>', '<extra_id_81>', '<extra_id_82>', '<extra_id_83>', '<extra_id_84>', '<extra_id_85>', '<extra_id_86>', '<extra_id_87>', '<extra_id_88>', '<extra_id_89>', '<extra_id_90>', '<extra_id_91>', '<extra_id_92>', '<extra_id_93>', '<extra_id_94>', '<extra_id_95>', '<extra_id_96>', '<extra_id_97>', '<extra_id_98>', '<extra_id_99>']}, clean_up_tokenization_spaces=True),  added_tokens_decoder={ 0: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 1: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 2: AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32000: AddedToken("<extra_id_99>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32001: AddedToken("<extra_id_98>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32002: AddedToken("<extra_id_97>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32003: AddedToken("<extra_id_96>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32004: AddedToken("<extra_id_95>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32005: AddedToken("<extra_id_94>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32006: AddedToken("<extra_id_93>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32007: AddedToken("<extra_id_92>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32008: AddedToken("<extra_id_91>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32009: AddedToken("<extra_id_90>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32010: AddedToken("<extra_id_89>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32011: AddedToken("<extra_id_88>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32012: AddedToken("<extra_id_87>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32013: AddedToken("<extra_id_86>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32014: AddedToken("<extra_id_85>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32015: AddedToken("<extra_id_84>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32016: AddedToken("<extra_id_83>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32017: AddedToken("<extra_id_82>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32018: AddedToken("<extra_id_81>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32019: AddedToken("<extra_id_80>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32020: AddedToken("<extra_id_79>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32021: AddedToken("<extra_id_78>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32022: AddedToken("<extra_id_77>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32023: AddedToken("<extra_id_76>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32024: AddedToken("<extra_id_75>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32025: AddedToken("<extra_id_74>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32026: AddedToken("<extra_id_73>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32027: AddedToken("<extra_id_72>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32028: AddedToken("<extra_id_71>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32029: AddedToken("<extra_id_70>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32030: AddedToken("<extra_id_69>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32031: AddedToken("<extra_id_68>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32032: AddedToken("<extra_id_67>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32033: AddedToken("<extra_id_66>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32034: AddedToken("<extra_id_65>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32035: AddedToken("<extra_id_64>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32036: AddedToken("<extra_id_63>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32037: AddedToken("<extra_id_62>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32038: AddedToken("<extra_id_61>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32039: AddedToken("<extra_id_60>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32040: AddedToken("<extra_id_59>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32041: AddedToken("<extra_id_58>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32042: AddedToken("<extra_id_57>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32043: AddedToken("<extra_id_56>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32044: AddedToken("<extra_id_55>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32045: AddedToken("<extra_id_54>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32046: AddedToken("<extra_id_53>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32047: AddedToken("<extra_id_52>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32048: AddedToken("<extra_id_51>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32049: AddedToken("<extra_id_50>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32050: AddedToken("<extra_id_49>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32051: AddedToken("<extra_id_48>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32052: AddedToken("<extra_id_47>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32053: AddedToken("<extra_id_46>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32054: AddedToken("<extra_id_45>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32055: AddedToken("<extra_id_44>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32056: AddedToken("<extra_id_43>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32057: AddedToken("<extra_id_42>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32058: AddedToken("<extra_id_41>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32059: AddedToken("<extra_id_40>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32060: AddedToken("<extra_id_39>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32061: AddedToken("<extra_id_38>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32062: AddedToken("<extra_id_37>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32063: AddedToken("<extra_id_36>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32064: AddedToken("<extra_id_35>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32065: AddedToken("<extra_id_34>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32066: AddedToken("<extra_id_33>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32067: AddedToken("<extra_id_32>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32068: AddedToken("<extra_id_31>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32069: AddedToken("<extra_id_30>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32070: AddedToken("<extra_id_29>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32071: AddedToken("<extra_id_28>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32072: AddedToken("<extra_id_27>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32073: AddedToken("<extra_id_26>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32074: AddedToken("<extra_id_25>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32075: AddedToken("<extra_id_24>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32076: AddedToken("<extra_id_23>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32077: AddedToken("<extra_id_22>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32078: AddedToken("<extra_id_21>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32079: AddedToken("<extra_id_20>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32080: AddedToken("<extra_id_19>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32081: AddedToken("<extra_id_18>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32082: AddedToken("<extra_id_17>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32083: AddedToken("<extra_id_16>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32084: AddedToken("<extra_id_15>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32085: AddedToken("<extra_id_14>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32086: AddedToken("<extra_id_13>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32087: AddedToken("<extra_id_12>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32088: AddedToken("<extra_id_11>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32089: AddedToken("<extra_id_10>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32090: AddedToken("<extra_id_9>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32091: AddedToken("<extra_id_8>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32092: AddedToken("<extra_id_7>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32093: AddedToken("<extra_id_6>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32094: AddedToken("<extra_id_5>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32095: AddedToken("<extra_id_4>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32096: AddedToken("<extra_id_3>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32097: AddedToken("<extra_id_2>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32098: AddedToken("<extra_id_1>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 32099: AddedToken("<extra_id_0>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), }