Convert tokens to ids. Args: tokens_list: word list Returns: index list

[summary] Args: golden_file_path (str): golden 集合路径 user_file_path (str): 用户预测结果路径 Returns: dict: the key is [F

Serializes this instance to a Python dictionary.

Checks whether `chars` is a whitespace character.

Calculate accuracy and f1 score. Args: golds: answers predicts: predictions given by model Returns: accuracy, f1 sco

Calculate accuracy and f1 score. Args: golds: answers predicts: predictions given by model Returns: accuracy, f1 sco

Find the most likely tag sequence using Viterbi algorithm. Args: emissions (`~torch.Tensor`): Emission score tensor of size

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Train model on train set and evaluate on train and valid set. Returns: state dict of the best model with highest valid f1 score

Train model on train set and evaluate on train and valid set. Returns: state dict of the best model with highest valid f1 score

Train model on train set and evaluate on train and valid set. Returns: state dict of the best model with highest valid f1 score

Conv1D layer as defined by Radford et al. for OpenAI GPT (and also used in GPT-2) Basically works like a Linear layer but the weights are

Checks whether `chars` is a punctuation character.

Calculate accuracy and f1 score. Args: golds: answers predicts: predictions given by model Returns: accuracy, f1 sco

Calculate accuracy and f1 score. Args: golds: answers predicts: predictions given by model Returns: accuracy, f1 sco

Find the most likely tag sequence using Viterbi algorithm. Args: emissions (`~torch.Tensor`): Emission score tensor of size

Load SMP-CAIL2020-Argmine train file and construct TensorDataset. Args: file_path: train file with last column as label

Serializes this instance to a JSON string.

Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the gi

Train model on train set and evaluate on train and valid set. Returns: state dict of the best model with highest valid f1 score

Checks whether `chars` is a control character.

get architecture model class

Converts a single index or a sequence of indices (integers) in a token " (resp.) a sequence of tokens (str/unicode), using the vocabulary

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

Convert tokens to ids. Args: tokens_list: word list Returns: index list

convert text-index into text-label.

Evaluate model on data loader in device. Args: model: model to be evaluate data_loader: torch.utils.data.DataLoader devic

Get csv logger. Args: log_file_name: file name title: first line in file log_format: default: '%(message)s' log_l

Get csv logger. Args: log_file_name: file name title: first line in file log_format: default: '%(message)s' log_l

Get csv logger. Args: log_file_name: file name title: first line in file log_format: default: '%(message)s' log_l

Get csv logger. Args: log_file_name: file name title: first line in file log_format: default: '%(message)s' log_l

Get labels on the last column from file. Args: filename: file name Returns: List[str]: label list

Create the path if it does not exist. Args: path: path to be used Returns: Existed path

Create the path if it does not exist. Args: path: path to be used Returns: Existed path

Create the path if it does not exist. Args: path: path to be used Returns: Existed path

Create the path if it does not exist. Args: path: path to be used Returns: Existed path

Create the path if it does not exist. Args: path: path to be used Returns: Existed path

Create the path if it does not exist. Args: path: path to be used Returns: Existed path