diff --git a/examples/run_ner.py b/examples/run_ner.py new file mode 100644 index 00000000000..ce048ade188 --- /dev/null +++ b/examples/run_ner.py @@ -0,0 +1,482 @@ +# coding=utf-8 +# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team. +# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +""" Fine-tuning the library models for named entity recognition on CoNLL-2003 (Bert). """ + +from __future__ import absolute_import, division, print_function + +import argparse +import glob +import logging +import os +import random + +import numpy as np +import torch +from seqeval.metrics import precision_score, recall_score, f1_score +from tensorboardX import SummaryWriter +from torch.nn import CrossEntropyLoss +from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset +from torch.utils.data.distributed import DistributedSampler +from tqdm import tqdm, trange +from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file + +from pytorch_transformers import AdamW, WarmupLinearSchedule +from pytorch_transformers import WEIGHTS_NAME, BertConfig, BertForTokenClassification, BertTokenizer + +logger = logging.getLogger(__name__) + +ALL_MODELS = sum( + (tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, )), + ()) + +MODEL_CLASSES = { + "bert": (BertConfig, BertForTokenClassification, BertTokenizer), +} + + +def set_seed(args): + random.seed(args.seed) + np.random.seed(args.seed) + torch.manual_seed(args.seed) + if args.n_gpu > 0: + torch.cuda.manual_seed_all(args.seed) + + +def train(args, train_dataset, model, tokenizer, pad_token_label_id): + """ Train the model """ + if args.local_rank in [-1, 0]: + tb_writer = SummaryWriter() + + args.train_batch_size = args.per_gpu_train_batch_size * max(1, args.n_gpu) + train_sampler = RandomSampler(train_dataset) if args.local_rank == -1 else DistributedSampler(train_dataset) + train_dataloader = DataLoader(train_dataset, sampler=train_sampler, batch_size=args.train_batch_size) + + if args.max_steps > 0: + t_total = args.max_steps + args.num_train_epochs = args.max_steps // (len(train_dataloader) // args.gradient_accumulation_steps) + 1 + else: + t_total = len(train_dataloader) // args.gradient_accumulation_steps * args.num_train_epochs + + # Prepare optimizer and schedule (linear warmup and decay) + no_decay = ["bias", "LayerNorm.weight"] + optimizer_grouped_parameters = [ + {"params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], + "weight_decay": args.weight_decay}, + {"params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0} + ] + optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon) + scheduler = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps, t_total=t_total) + if args.fp16: + try: + from apex import amp + except ImportError: + raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.") + model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level) + + # multi-gpu training (should be after apex fp16 initialization) + if args.n_gpu > 1: + model = torch.nn.DataParallel(model) + + # Distributed training (should be after apex fp16 initialization) + if args.local_rank != -1: + model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank], + output_device=args.local_rank, + find_unused_parameters=True) + + # Train! + logger.info("***** Running training *****") + logger.info(" Num examples = %d", len(train_dataset)) + logger.info(" Num Epochs = %d", args.num_train_epochs) + logger.info(" Instantaneous batch size per GPU = %d", args.per_gpu_train_batch_size) + logger.info(" Total train batch size (w. parallel, distributed & accumulation) = %d", + args.train_batch_size * args.gradient_accumulation_steps * ( + torch.distributed.get_world_size() if args.local_rank != -1 else 1)) + logger.info(" Gradient Accumulation steps = %d", args.gradient_accumulation_steps) + logger.info(" Total optimization steps = %d", t_total) + + global_step = 0 + tr_loss, logging_loss = 0.0, 0.0 + model.zero_grad() + train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]) + set_seed(args) # Added here for reproductibility (even between python 2 and 3) + for _ in train_iterator: + epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0]) + for step, batch in enumerate(epoch_iterator): + model.train() + batch = tuple(t.to(args.device) for t in batch) + inputs = {"input_ids": batch[0], + "attention_mask": batch[1], + "token_type_ids": batch[2] if args.model_type in ["bert", "xlnet"] else None, + # XLM and RoBERTa don"t use segment_ids + "labels": batch[3]} + outputs = model(**inputs) + loss = outputs[0] # model outputs are always tuple in pytorch-transformers (see doc) + + if args.n_gpu > 1: + loss = loss.mean() # mean() to average on multi-gpu parallel training + if args.gradient_accumulation_steps > 1: + loss = loss / args.gradient_accumulation_steps + + if args.fp16: + with amp.scale_loss(loss, optimizer) as scaled_loss: + scaled_loss.backward() + torch.nn.utils.clip_grad_norm_(amp.master_params(optimizer), args.max_grad_norm) + else: + loss.backward() + torch.nn.utils.clip_grad_norm_(model.parameters(), args.max_grad_norm) + + tr_loss += loss.item() + if (step + 1) % args.gradient_accumulation_steps == 0: + scheduler.step() # Update learning rate schedule + optimizer.step() + model.zero_grad() + global_step += 1 + + if args.local_rank in [-1, 0] and args.logging_steps > 0 and global_step % args.logging_steps == 0: + # Log metrics + if args.local_rank == -1 and args.evaluate_during_training: # Only evaluate when single GPU otherwise metrics may not average well + results = evaluate(args, model, tokenizer, pad_token_label_id) + for key, value in results.items(): + tb_writer.add_scalar("eval_{}".format(key), value, global_step) + tb_writer.add_scalar("lr", scheduler.get_lr()[0], global_step) + tb_writer.add_scalar("loss", (tr_loss - logging_loss) / args.logging_steps, global_step) + logging_loss = tr_loss + + if args.local_rank in [-1, 0] and args.save_steps > 0 and global_step % args.save_steps == 0: + # Save model checkpoint + output_dir = os.path.join(args.output_dir, "checkpoint-{}".format(global_step)) + if not os.path.exists(output_dir): + os.makedirs(output_dir) + model_to_save = model.module if hasattr(model, + "module") else model # Take care of distributed/parallel training + model_to_save.save_pretrained(output_dir) + torch.save(args, os.path.join(output_dir, "training_args.bin")) + logger.info("Saving model checkpoint to %s", output_dir) + + if args.max_steps > 0 and global_step > args.max_steps: + epoch_iterator.close() + break + if args.max_steps > 0 and global_step > args.max_steps: + train_iterator.close() + break + + if args.local_rank in [-1, 0]: + tb_writer.close() + + return global_step, tr_loss / global_step + + +def evaluate(args, model, tokenizer, pad_token_label_id, prefix=""): + eval_dataset = load_and_cache_examples(args, tokenizer, pad_token_label_id, evaluate=True) + + args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu) + # Note that DistributedSampler samples randomly + eval_sampler = SequentialSampler(eval_dataset) if args.local_rank == -1 else DistributedSampler(eval_dataset) + eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size) + + # Eval! + logger.info("***** Running evaluation %s *****", prefix) + logger.info(" Num examples = %d", len(eval_dataset)) + logger.info(" Batch size = %d", args.eval_batch_size) + eval_loss = 0.0 + nb_eval_steps = 0 + preds = None + out_label_ids = None + model.eval() + for batch in tqdm(eval_dataloader, desc="Evaluating"): + batch = tuple(t.to(args.device) for t in batch) + + with torch.no_grad(): + inputs = {"input_ids": batch[0], + "attention_mask": batch[1], + "token_type_ids": batch[2] if args.model_type in ["bert", "xlnet"] else None, + # XLM and RoBERTa don"t use segment_ids + "labels": batch[3]} + outputs = model(**inputs) + tmp_eval_loss, logits = outputs[:2] + + eval_loss += tmp_eval_loss.item() + nb_eval_steps += 1 + if preds is None: + preds = logits.detach().cpu().numpy() + out_label_ids = inputs["labels"].detach().cpu().numpy() + else: + preds = np.append(preds, logits.detach().cpu().numpy(), axis=0) + out_label_ids = np.append(out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0) + + eval_loss = eval_loss / nb_eval_steps + preds = np.argmax(preds, axis=2) + + label_map = {i: label for i, label in enumerate(get_labels())} + + out_label_list = [[] for _ in range(out_label_ids.shape[0])] + preds_list = [[] for _ in range(out_label_ids.shape[0])] + + for i in range(out_label_ids.shape[0]): + for j in range(out_label_ids.shape[1]): + if out_label_ids[i, j] != pad_token_label_id: + out_label_list[i].append(label_map[out_label_ids[i][j]]) + preds_list[i].append(label_map[preds[i][j]]) + + results = { + "loss": eval_loss, + "precision": precision_score(out_label_list, preds_list), + "recall": recall_score(out_label_list, preds_list), + "f1": f1_score(out_label_list, preds_list) + } + + logger.info("***** Eval results %s *****", prefix) + for key in sorted(results.keys()): + logger.info(" %s = %s", key, str(results[key])) + + return results + + +def load_and_cache_examples(args, tokenizer, pad_token_label_id, evaluate=False): + if args.local_rank not in [-1, 0] and not evaluate: + torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache + + # Load data features from cache or dataset file + cached_features_file = os.path.join(args.data_dir, "cached_{}_{}_{}".format("dev" if evaluate else "train", + list(filter(None, args.model_name_or_path.split("/"))).pop(), + str(args.max_seq_length))) + if os.path.exists(cached_features_file): + logger.info("Loading features from cached file %s", cached_features_file) + features = torch.load(cached_features_file) + else: + logger.info("Creating features from dataset file at %s", args.data_dir) + label_list = get_labels() + examples = read_examples_from_file(args.data_dir, evaluate=evaluate) + features = convert_examples_to_features(examples, label_list, args.max_seq_length, tokenizer, + cls_token_at_end=bool(args.model_type in ["xlnet"]), + # xlnet has a cls token at the end + cls_token=tokenizer.cls_token, + cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0, + sep_token=tokenizer.sep_token, + sep_token_extra=bool(args.model_type in ["roberta"]), + # roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805 + pad_on_left=bool(args.model_type in ["xlnet"]), + # pad on the left for xlnet + pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0], + pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0, + pad_token_label_id=pad_token_label_id + ) + if args.local_rank in [-1, 0]: + logger.info("Saving features into cached file %s", cached_features_file) + torch.save(features, cached_features_file) + + if args.local_rank == 0 and not evaluate: + torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache + + # Convert to Tensors and build dataset + all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long) + all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long) + all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long) + all_label_ids = torch.tensor([f.label_ids for f in features], dtype=torch.long) + + dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids) + return dataset + + +def main(): + parser = argparse.ArgumentParser() + + ## Required parameters + parser.add_argument("--data_dir", default=None, type=str, required=True, + help="The input data dir. Should contain the training files for the CoNLL-2003 NER task.") + parser.add_argument("--model_type", default=None, type=str, required=True, + help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys())) + parser.add_argument("--model_name_or_path", default=None, type=str, required=True, + help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS)) + parser.add_argument("--output_dir", default=None, type=str, required=True, + help="The output directory where the model predictions and checkpoints will be written.") + + ## Other parameters + parser.add_argument("--config_name", default="", type=str, + help="Pretrained config name or path if not the same as model_name") + parser.add_argument("--tokenizer_name", default="", type=str, + help="Pretrained tokenizer name or path if not the same as model_name") + parser.add_argument("--cache_dir", default="", type=str, + help="Where do you want to store the pre-trained models downloaded from s3") + parser.add_argument("--max_seq_length", default=128, type=int, + help="The maximum total input sequence length after tokenization. Sequences longer " + "than this will be truncated, sequences shorter will be padded.") + parser.add_argument("--do_train", action="store_true", + help="Whether to run training.") + parser.add_argument("--do_eval", action="store_true", + help="Whether to run eval on the dev set.") + parser.add_argument("--evaluate_during_training", action="store_true", + help="Whether to run evaluation during training at each logging step.") + parser.add_argument("--do_lower_case", action="store_true", + help="Set this flag if you are using an uncased model.") + + parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, + help="Batch size per GPU/CPU for training.") + parser.add_argument("--per_gpu_eval_batch_size", default=8, type=int, + help="Batch size per GPU/CPU for evaluation.") + parser.add_argument("--gradient_accumulation_steps", type=int, default=1, + help="Number of updates steps to accumulate before performing a backward/update pass.") + parser.add_argument("--learning_rate", default=5e-5, type=float, + help="The initial learning rate for Adam.") + parser.add_argument("--weight_decay", default=0.0, type=float, + help="Weight decay if we apply some.") + parser.add_argument("--adam_epsilon", default=1e-8, type=float, + help="Epsilon for Adam optimizer.") + parser.add_argument("--max_grad_norm", default=1.0, type=float, + help="Max gradient norm.") + parser.add_argument("--num_train_epochs", default=3.0, type=float, + help="Total number of training epochs to perform.") + parser.add_argument("--max_steps", default=-1, type=int, + help="If > 0: set total number of training steps to perform. Override num_train_epochs.") + parser.add_argument("--warmup_steps", default=0, type=int, + help="Linear warmup over warmup_steps.") + + parser.add_argument("--logging_steps", type=int, default=50, + help="Log every X updates steps.") + parser.add_argument("--save_steps", type=int, default=50, + help="Save checkpoint every X updates steps.") + parser.add_argument("--eval_all_checkpoints", action="store_true", + help="Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number") + parser.add_argument("--no_cuda", action="store_true", + help="Avoid using CUDA when available") + parser.add_argument("--overwrite_output_dir", action="store_true", + help="Overwrite the content of the output directory") + parser.add_argument("--overwrite_cache", action="store_true", + help="Overwrite the cached training and evaluation sets") + parser.add_argument("--seed", type=int, default=42, + help="random seed for initialization") + + parser.add_argument("--fp16", action="store_true", + help="Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit") + parser.add_argument("--fp16_opt_level", type=str, default="O1", + help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']." + "See details at https://nvidia.github.io/apex/amp.html") + parser.add_argument("--local_rank", type=int, default=-1, + help="For distributed training: local_rank") + parser.add_argument("--server_ip", type=str, default="", help="For distant debugging.") + parser.add_argument("--server_port", type=str, default="", help="For distant debugging.") + args = parser.parse_args() + + if os.path.exists(args.output_dir) and os.listdir( + args.output_dir) and args.do_train and not args.overwrite_output_dir: + raise ValueError( + "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format( + args.output_dir)) + + # Setup distant debugging if needed + if args.server_ip and args.server_port: + # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script + import ptvsd + print("Waiting for debugger attach") + ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) + ptvsd.wait_for_attach() + + # Setup CUDA, GPU & distributed training + if args.local_rank == -1 or args.no_cuda: + device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") + args.n_gpu = torch.cuda.device_count() + else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs + torch.cuda.set_device(args.local_rank) + device = torch.device("cuda", args.local_rank) + torch.distributed.init_process_group(backend="nccl") + args.n_gpu = 1 + args.device = device + + # Setup logging + logging.basicConfig(format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", + datefmt="%m/%d/%Y %H:%M:%S", + level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN) + logger.warning("Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", + args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16) + + # Set seed + set_seed(args) + + # Prepare CONLL-2003 task + label_list = get_labels() + num_labels = len(label_list) + # Use cross entropy ignore index as padding label id so that only real label ids contribute to the loss later + pad_token_label_id = CrossEntropyLoss().ignore_index + + # Load pretrained model and tokenizer + if args.local_rank not in [-1, 0]: + torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab + + args.model_type = args.model_type.lower() + config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] + config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path, + num_labels=num_labels) + tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, + do_lower_case=args.do_lower_case) + model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path), + config=config) + + if args.local_rank == 0: + torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab + + model.to(args.device) + + logger.info("Training/evaluation parameters %s", args) + + # Training + if args.do_train: + train_dataset = load_and_cache_examples(args, tokenizer, pad_token_label_id, evaluate=False) + global_step, tr_loss = train(args, train_dataset, model, tokenizer, pad_token_label_id) + logger.info(" global_step = %s, average loss = %s", global_step, tr_loss) + + # Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained() + if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): + # Create output directory if needed + if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]: + os.makedirs(args.output_dir) + + logger.info("Saving model checkpoint to %s", args.output_dir) + # Save a trained model, configuration and tokenizer using `save_pretrained()`. + # They can then be reloaded using `from_pretrained()` + model_to_save = model.module if hasattr(model, "module") else model # Take care of distributed/parallel training + model_to_save.save_pretrained(args.output_dir) + tokenizer.save_pretrained(args.output_dir) + + # Good practice: save your training arguments together with the trained model + torch.save(args, os.path.join(args.output_dir, "training_args.bin")) + + # Evaluation + results = {} + if args.do_eval and args.local_rank in [-1, 0]: + tokenizer = tokenizer_class.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case) + checkpoints = [args.output_dir] + if args.eval_all_checkpoints: + checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME, recursive=True))) + logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN) # Reduce logging + logger.info("Evaluate the following checkpoints: %s", checkpoints) + for checkpoint in checkpoints: + global_step = checkpoint.split("-")[-1] if len(checkpoints) > 1 else "" + model = model_class.from_pretrained(checkpoint) + model.to(args.device) + result = evaluate(args, model, tokenizer, pad_token_label_id, prefix=global_step) + if global_step: + result = {"{}_{}".format(global_step, k): v for k, v in result.items()} + results.update(result) + output_eval_file = os.path.join(args.output_dir, "eval_results.txt") + with open(output_eval_file, "w") as writer: + for key in sorted(results.keys()): + writer.write("{} = {}\n".format(key, str(results[key]))) + + return results + + +if __name__ == "__main__": + main() diff --git a/examples/utils_ner.py b/examples/utils_ner.py new file mode 100644 index 00000000000..0d3af3e061a --- /dev/null +++ b/examples/utils_ner.py @@ -0,0 +1,206 @@ +# coding=utf-8 +# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team. +# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +""" Named entity recognition fine-tuning: utilities to work with CoNLL-2003 task. """ + +from __future__ import absolute_import, division, print_function + +import logging +import os +from io import open + +logger = logging.getLogger(__name__) + + +class InputExample(object): + """A single training/test example for token classification.""" + + def __init__(self, guid, words, labels): + """Constructs a InputExample. + + Args: + guid: Unique id for the example. + words: list. The words of the sequence. + labels: (Optional) list. The labels for each word of the sequence. This should be + specified for train and dev examples, but not for test examples. + """ + self.guid = guid + self.words = words + self.labels = labels + + +class InputFeatures(object): + """A single set of features of data.""" + + def __init__(self, input_ids, input_mask, segment_ids, label_ids): + self.input_ids = input_ids + self.input_mask = input_mask + self.segment_ids = segment_ids + self.label_ids = label_ids + + +def read_examples_from_file(data_dir, evaluate=False): + if evaluate: + file_path = os.path.join(data_dir, "dev.txt") + guid_prefix = "dev" + else: + file_path = os.path.join(data_dir, "train.txt") + guid_prefix = "train" + guid_index = 1 + examples = [] + with open(file_path, encoding="utf-8") as f: + words = [] + labels = [] + for line in f: + if line.startswith("-DOCSTART-") or line == "" or line == "\n": + if words: + examples.append(InputExample(guid="{}-{}".format(guid_prefix, guid_index), + words=words, + labels=labels)) + guid_index += 1 + words = [] + labels = [] + else: + splits = line.split(" ") + words.append(splits[0]) + labels.append(splits[-1][:-1]) + if words: + examples.append(InputExample(guid="%s-%d".format(guid_prefix, guid_index), + words=words, + labels=labels)) + return examples + + +def convert_examples_to_features(examples, + label_list, + max_seq_length, + tokenizer, + cls_token_at_end=False, + cls_token="[CLS]", + cls_token_segment_id=1, + sep_token="[SEP]", + sep_token_extra=False, + pad_on_left=False, + pad_token=0, + pad_token_segment_id=0, + pad_token_label_id=-1, + sequence_a_segment_id=0, + mask_padding_with_zero=True): + """ Loads a data file into a list of `InputBatch`s + `cls_token_at_end` define the location of the CLS token: + - False (Default, BERT/XLM pattern): [CLS] + A + [SEP] + B + [SEP] + - True (XLNet/GPT pattern): A + [SEP] + B + [SEP] + [CLS] + `cls_token_segment_id` define the segment id associated to the CLS token (0 for BERT, 2 for XLNet) + """ + + label_map = {label: i for i, label in enumerate(label_list)} + + features = [] + for (ex_index, example) in enumerate(examples): + if ex_index % 10000 == 0: + logger.info("Writing example %d of %d", ex_index, len(examples)) + + tokens = [] + label_ids = [] + for word, label in zip(example.words, example.labels): + word_tokens = tokenizer.tokenize(word) + tokens.extend(word_tokens) + # Use the real label id for the first token of the word, and padding ids for the remaining tokens + label_ids.extend([label_map[label]] + [pad_token_label_id] * (len(word_tokens) - 1)) + + # Account for [CLS] and [SEP] with "- 2" and with "- 3" for RoBERTa. + special_tokens_count = 3 if sep_token_extra else 2 + if len(tokens) > max_seq_length - special_tokens_count: + tokens = tokens[:(max_seq_length - special_tokens_count)] + label_ids = label_ids[:(max_seq_length - special_tokens_count)] + + # 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 unambiguously 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 += [sep_token] + label_ids += [pad_token_label_id] + if sep_token_extra: + # roberta uses an extra separator b/w pairs of sentences + tokens += [sep_token] + label_ids += [pad_token_label_id] + segment_ids = [sequence_a_segment_id] * len(tokens) + + if cls_token_at_end: + tokens += [cls_token] + label_ids += [pad_token_label_id] + segment_ids += [cls_token_segment_id] + else: + tokens = [cls_token] + tokens + label_ids = [pad_token_label_id] + label_ids + segment_ids = [cls_token_segment_id] + segment_ids + + 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 if mask_padding_with_zero else 0] * len(input_ids) + + # Zero-pad up to the sequence length. + padding_length = max_seq_length - len(input_ids) + if pad_on_left: + input_ids = ([pad_token] * padding_length) + input_ids + input_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + input_mask + segment_ids = ([pad_token_segment_id] * padding_length) + segment_ids + label_ids = ([pad_token_label_id] * padding_length) + label_ids + else: + input_ids += ([pad_token] * padding_length) + input_mask += ([0 if mask_padding_with_zero else 1] * padding_length) + segment_ids += ([pad_token_segment_id] * padding_length) + label_ids += ([pad_token_label_id] * padding_length) + + assert len(input_ids) == max_seq_length + assert len(input_mask) == max_seq_length + assert len(segment_ids) == max_seq_length + assert len(label_ids) == max_seq_length + + if ex_index < 5: + logger.info("*** Example ***") + logger.info("guid: %s", example.guid) + logger.info("tokens: %s", " ".join([str(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_ids: %s", " ".join([str(x) for x in label_ids])) + + features.append( + InputFeatures(input_ids=input_ids, + input_mask=input_mask, + segment_ids=segment_ids, + label_ids=label_ids)) + return features + + +def get_labels(): + return ["O", "B-MISC", "I-MISC", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC"]