Skip to content

Vocabularies created before tokenization #7

Description

@mattiadg

In get_s2s_data the training files are scanned to find the vocabulary, and only after that they are tokenized, using the vocabulary for converting the tokens into indeces.

mxnet_seq2seq/utils.py

Lines 99 to 102 in c57d892

src_dict, inv_src_dict = top_words_train_valid(src_train_path, src_valid_path)
print("Tokenizing src_train_path")
src_train_sent = tokenize_text(src_train_path, vocab=src_dict)

I think the order should be -> tokenization -> vocabulary -> convert into indeces

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions