crosslingual_dataset¶

Module Contents¶

`_BilingualDataset`
`CrosslingualDataset`

class _BilingualDataset(bow_en, bow_cn)¶

Bases: torch.utils.data.Dataset

bow_en¶

bow_cn¶

bow_size_en¶

bow_size_cn¶

__len__()¶

__getitem__(index)¶

class CrosslingualDataset(dataset_dir, lang1, lang2, dict_path, device='cpu', batch_size=200, as_tensor=True)¶

batch_size = 200¶

train_size_en = 0¶

train_size_cn = 0¶

vocab_size_en = 0¶

vocab_size_cn = 0¶

pretrained_WE_en¶

pretrained_WE_cn¶

Map_en2cn¶

Map_cn2en¶

move_to_device(bow, device)¶

read_data(dataset_dir, lang)¶

parse_dictionary(dict_path)¶

get_Map(trans_matrix, bow)¶