def __repr__(self): s = "" s += "qas_id: %s" % (printable_text(self.qas_id)) s += ", question_text: %s" % (printable_text(self.question_text)) s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens)) s += ", answerable: [%s]" % (self.answerable) return s
def __repr__(self): s = "" s += "qas_id: %s" % (printable_text(self.qas_id)) s += ", question_text: %s" % (printable_text(self.question_text)) s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens)) if self.start_position: s += ", start_position: %d" % (self.start_position) if self.start_position: s += ", end_position: %d" % (self.end_position) return s
def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" label_map = {} for (i, label) in enumerate(label_list): label_map[label] = i features = [] for (ex_index, example) in enumerate(examples): tokens_a = tokenizer.tokenize(example.text_a) tokens_b = None if example.text_b: tokens_b = tokenizer.tokenize(example.text_b) if tokens_b: # Modifies `tokens_a` and `tokens_b` in place so that the total # length is less than the specified length. # Account for [CLS], [SEP], [SEP] with "- 3" _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3) else: # Account for [CLS] and [SEP] with "- 2" if len(tokens_a) > max_seq_length - 2: tokens_a = tokens_a[0:(max_seq_length - 2)] # The convention in BERT is: # (a) For sequence pairs: # tokens: [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP] # type_ids: 0 0 0 0 0 0 0 0 1 1 1 1 1 1 # (b) For single sequences: # tokens: [CLS] the dog is hairy . [SEP] # type_ids: 0 0 0 0 0 0 0 # # Where "type_ids" are used to indicate whether this is the first # sequence or the second sequence. The embedding vectors for `type=0` and # `type=1` were learned during pre-training and are added to the wordpiece # embedding vector (and position vector). This is not *strictly* necessary # since the [SEP] token unambigiously separates the sequences, but it makes # it easier for the model to learn the concept of sequences. # # For classification tasks, the first vector (corresponding to [CLS]) is # used as as the "sentence vector". Note that this only makes sense because # the entire model is fine-tuned. tokens = [] segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for token in tokens_a: tokens.append(token) segment_ids.append(0) tokens.append("[SEP]") segment_ids.append(0) if tokens_b: for token in tokens_b: tokens.append(token) segment_ids.append(1) tokens.append("[SEP]") segment_ids.append(1) input_ids = tokenizer.convert_tokens_to_ids(tokens) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. input_mask = [1] * len(input_ids) # Zero-pad up to the sequence length. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length label_id = label_map[example.label] if ex_index < 5: logger.info("*** Example ***") logger.info("guid: %s" % (example.guid)) logger.info("tokens: %s" % " ".join([printable_text(x) for x in tokens])) logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids])) logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask])) logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids])) logger.info("label: %s (id = %d)" % (example.label, label_id)) features.append( InputFeatures(input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_id=label_id)) return features
def convert_examples_to_features(examples, tokenizer, max_seq_length, doc_stride, max_query_length, is_training): """Loads a data file into a list of `InputBatch`s.""" unique_id = 1000000000 features = [] for (example_index, example) in enumerate(examples): query_tokens = tokenizer.tokenize(example.question_text) if len(query_tokens) > max_query_length: query_tokens = query_tokens[0:max_query_length] tok_to_orig_index = [] orig_to_tok_index = [] all_doc_tokens = [] for (i, token) in enumerate(example.doc_tokens): orig_to_tok_index.append(len(all_doc_tokens)) sub_tokens = tokenizer.tokenize(token) for sub_token in sub_tokens: tok_to_orig_index.append(i) all_doc_tokens.append(sub_token) tok_start_position = None tok_end_position = None if is_training: tok_start_position = orig_to_tok_index[example.start_position] if example.end_position < len(example.doc_tokens) - 1: tok_end_position = orig_to_tok_index[example.end_position + 1] - 1 else: tok_end_position = len(all_doc_tokens) - 1 (tok_start_position, tok_end_position) = _improve_answer_span( all_doc_tokens, tok_start_position, tok_end_position, tokenizer, example.orig_answer_text) # The -3 accounts for [CLS], [SEP] and [SEP] max_tokens_for_doc = max_seq_length - len(query_tokens) - 3 # We can have documents that are longer than the maximum sequence length. # To deal with this we do a sliding window approach, where we take chunks # of the up to our max length with a stride of `doc_stride`. _DocSpan = collections.namedtuple( # pylint: disable=invalid-name "DocSpan", ["start", "length"]) doc_spans = [] start_offset = 0 while start_offset < len(all_doc_tokens): length = len(all_doc_tokens) - start_offset if length > max_tokens_for_doc: length = max_tokens_for_doc doc_spans.append(_DocSpan(start=start_offset, length=length)) if start_offset + length == len(all_doc_tokens): break start_offset += min(length, doc_stride) for (doc_span_index, doc_span) in enumerate(doc_spans): tokens = [] token_to_orig_map = {} token_is_max_context = {} segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for token in query_tokens: tokens.append(token) segment_ids.append(0) tokens.append("[SEP]") segment_ids.append(0) for i in range(doc_span.length): split_token_index = doc_span.start + i token_to_orig_map[len( tokens)] = tok_to_orig_index[split_token_index] is_max_context = _check_is_max_context(doc_spans, doc_span_index, split_token_index) token_is_max_context[len(tokens)] = is_max_context tokens.append(all_doc_tokens[split_token_index]) segment_ids.append(1) tokens.append("[SEP]") segment_ids.append(1) input_ids = tokenizer.convert_tokens_to_ids(tokens) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. input_mask = [1] * len(input_ids) # Zero-pad up to the sequence length. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length start_position = None end_position = None if is_training: # For training, if our document chunk does not contain an annotation # we throw it out, since there is nothing to predict. doc_start = doc_span.start doc_end = doc_span.start + doc_span.length - 1 if (example.start_position < doc_start or example.end_position < doc_start or example.start_position > doc_end or example.end_position > doc_end): continue doc_offset = len(query_tokens) + 2 start_position = tok_start_position - doc_start + doc_offset end_position = tok_end_position - doc_start + doc_offset if example_index < 20: logger.info("*** Example ***") logger.info("unique_id: %s" % (unique_id)) logger.info("example_index: %s" % (example_index)) logger.info("doc_span_index: %s" % (doc_span_index)) logger.info("tokens: %s" % " ".join([printable_text(x) for x in tokens])) logger.info("token_to_orig_map: %s" % " ".join( ["%d:%d" % (x, y) for (x, y) in token_to_orig_map.items()])) logger.info("token_is_max_context: %s" % " ".join([ "%d:%s" % (x, y) for (x, y) in token_is_max_context.items() ])) logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids])) logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask])) logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids])) if is_training: answer_text = " ".join( tokens[start_position:(end_position + 1)]) logger.info("start_position: %d" % (start_position)) logger.info("end_position: %d" % (end_position)) logger.info("answer: %s" % (printable_text(answer_text))) features.append( InputFeatures(unique_id=unique_id, example_index=example_index, doc_span_index=doc_span_index, tokens=tokens, token_to_orig_map=token_to_orig_map, token_is_max_context=token_is_max_context, input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, start_position=start_position, end_position=end_position)) unique_id += 1 return features
def convert_examples_to_features_mc(examples, label_list, max_seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" label_map = {} for (i, label) in enumerate(label_list): label_map[label] = i features = [] for (ex_index, example) in tqdm(enumerate(examples), desc="Converting examples"): inputs = [] tokens_a = [tokenizer.tokenize(t) for t in example.text_a] inputs.append(tokens_a) tokens_b = None if example.text_b: tokens_b = [tokenizer.tokenize(t) for t in example.text_b] inputs.append(tokens_b) tokens_c = None if example.text_c: tokens_c = [tokenizer.tokenize(t) for t in example.text_c] inputs.append(tokens_c) tokens_d = None if example.text_d: tokens_d = [tokenizer.tokenize(t) for t in example.text_d] inputs.append(tokens_d) if len(inputs) > 1: # Modifies `tokens_a` and `tokens_b` in place so that the total # length is less than the specified length. # Account for [CLS], [SEP], [SEP] with "- 3" adjusted_len = max_seq_length - len(inputs) - 1 _truncate_sequences(adjusted_len, inputs) else: # Account for [CLS] and [SEP] with "- 2" for idx, ta in enumerate(tokens_a): tokens_a[idx] = tokens_a[idx][0:(max_seq_length - 2)] all_tokens = [] all_token_ids = [] all_segments = [] all_masks = [] for zipped_tokens in zip(*inputs): tokens = [] segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for idx, field in enumerate(zipped_tokens): for token in field: tokens.append(token) segment_ids.append(idx) tokens.append("[SEP]") segment_ids.append(idx) input_ids = tokenizer.convert_tokens_to_ids(tokens) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. input_mask = [1] * len(input_ids) # Zero-pad up to the sequence length. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) if len(input_ids) != max_seq_length: print("FOUND") assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length all_tokens.append(tokens) all_token_ids.append(input_ids) all_segments.append(segment_ids) all_masks.append(input_mask) label_id = label_map[example.label] if ex_index < 5: logger.info("\n\n") logger.info("*** Example {} ***\n".format(ex_index)) logger.info("guid: %s" % (example.guid)) _ts = all_tokens _ids = all_token_ids _masks = all_masks _segs = all_segments logger.info("\n") for idx, (_t, _id, _mask, _seg) in enumerate(zip(_ts, _ids, _masks, _segs)): logger.info("\tOption {}".format(idx)) logger.info("\ttokens: %s" % " ".join([printable_text(x) for x in _t])) logger.info("\tinput_ids: %s" % " ".join([str(x) for x in _id])) logger.info("\tinput_mask: %s" % " ".join([str(x) for x in _mask])) logger.info("\tsegment_ids: %s" % " ".join([str(x) for x in _seg])) logger.info("label: %s (id = %d)" % (example.label, label_id)) features.append( InputFeatures(input_ids=all_token_ids, input_mask=all_masks, segment_ids=all_segments, label_id=label_id)) return features
def convert_examples_to_features(examples, tokenizer, max_seq_length, doc_stride, max_query_length, is_training): unique_id = 1000000000 long_input_features = [] for (example_index, example) in enumerate(tqdm(examples, desc="Example")): input_features = [] query_tokens = tokenizer.tokenize(example.question_text) if len(query_tokens) > max_query_length: query_tokens = query_tokens[0:max_query_length] all_doc_tokens = [] for (i, token) in enumerate(example.doc_tokens): sub_tokens = tokenizer.tokenize(token) for sub_token in sub_tokens: all_doc_tokens.append(sub_token) # The -3 accounts for [CLS], [SEP] and [SEP] max_tokens_for_doc = max_seq_length - len(query_tokens) - 3 # We can have documents that are longer than the maximum sequence length. # To deal with this we do a sliding window approach, where we take chunks # of the up to our max length with a stride of `doc_stride`. _DocSpan = collections.namedtuple( # pylint: disable=invalid-name "DocSpan", ["start", "length"]) doc_spans = [] start_offset = 0 while start_offset < len(all_doc_tokens): length = len(all_doc_tokens) - start_offset if length > max_tokens_for_doc: length = max_tokens_for_doc doc_spans.append(_DocSpan(start=start_offset, length=length)) if start_offset + length == len(all_doc_tokens): break start_offset += min(length, doc_stride) for (doc_span_index, doc_span) in enumerate(doc_spans): tokens = [] segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for token in query_tokens: tokens.append(token) segment_ids.append(0) tokens.append("[SEP]") segment_ids.append(0) for i in range(doc_span.length): split_token_index = doc_span.start + i tokens.append(all_doc_tokens[split_token_index]) segment_ids.append(1) tokens.append("[SEP]") segment_ids.append(1) input_ids = tokenizer.convert_tokens_to_ids(tokens) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. input_mask = [1] * len(input_ids) # Zero-pad up to the sequence length. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length if example_index < 20: logger.info("*** Example ***") logger.info("unique_id: %s" % (unique_id)) logger.info("example_index: %s" % (example_index)) logger.info("doc_span_index: %s" % (doc_span_index)) logger.info("tokens: %s" % " ".join([printable_text(x) for x in tokens])) logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids])) logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask])) logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids])) input_features.append( InputFeature(input_ids=input_ids, token_type_ids=segment_ids, attention_mask=input_mask)) long_input_features.append( LongInputFeature( example.qas_id, input_features, int(example.answerable) if example.answerable is not None else None)) unique_id += 1 return long_input_features
def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer): """Loads a data file into a list of `InputBatch`s.""" print("#examples", len(examples)) label_map = {} for (i, label) in enumerate(label_list): label_map[label] = i features = [[]] for (ex_index, example) in enumerate(examples): tokens_a = tokenizer.tokenize(example.text_a) tokens_b = None tokens_c = None if example.text_b: tokens_b = tokenizer.tokenize(example.text_b) if example.text_c: tokens_c = tokenizer.tokenize(example.text_c) if tokens_c: _truncate_seq_tuple(tokens_a, tokens_b, tokens_c, max_seq_length - 4) tokens_b = tokens_c + ["[SEP]"] + tokens_b elif tokens_b: _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3) else: if len(tokens_a) > max_seq_length - 2: tokens_a = tokens_a[0:(max_seq_length - 2)] tokens = [] segment_ids = [] tokens.append("[CLS]") segment_ids.append(0) for token in tokens_a: tokens.append(token) segment_ids.append(0) tokens.append("[SEP]") segment_ids.append(0) if tokens_b: for token in tokens_b: tokens.append(token) segment_ids.append(1) tokens.append("[SEP]") segment_ids.append(1) input_ids = tokenizer.convert_tokens_to_ids(tokens) # The mask has 1 for real tokens and 0 for padding tokens. Only real # tokens are attended to. input_mask = [1] * len(input_ids) # Zero-pad up to the sequence length. while len(input_ids) < max_seq_length: input_ids.append(0) input_mask.append(0) segment_ids.append(0) assert len(input_ids) == max_seq_length assert len(input_mask) == max_seq_length assert len(segment_ids) == max_seq_length label_id = label_map[example.label] if ex_index < 5: logger.info("*** Example ***") logger.info("guid: %s" % (example.guid)) logger.info( "tokens: %s" % " ".join([tokenization.printable_text(x) for x in tokens])) logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids])) logger.info("input_mask: %s" % " ".join([str(x) for x in input_mask])) logger.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids])) logger.info("label: %s (id = %d)" % (example.label, label_id)) features[-1].append( InputFeatures(input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids, label_id=label_id)) if len(features[-1]) == n_class: features.append([]) if len(features[-1]) == 0: features = features[:-1] print('#features', len(features)) return features