CLI.ner.entity_extractor¶
About:¶
This command processes an input text and returns named entites for each token within the text. As follows:
Usage:¶
Below is the usage information that can be generated by running entity_extractor --help.
entity_extractor --text=INPUT_TEXT
entity_extractor --dir=DIRECTORY_PATH --output_csv "path/to/csv/file"
Options:¶
--text INPUT_TEXT
The text that needs to be analyzed for Named Entity Recognition.
--dir DIRECTORY_PATH
Directory containing the text files to be analyzed for Named Entity Recognition
--output_csv CSV_FILE
The path for output csv file
Examples:¶
entity_extractor --text "Your text here"
entity_extractor --dir "path/to/your/dir" --output_csv "path/to/your/file"
CLI.ner.corpus_entity_extractor¶
About:¶
The following command takes a CSV file as input. It splits a specific column into tokens and tags them using named entity recognition (NER). It retains all other columns as they are, and it also adds sentences and tokens. Additionally, it assigns an auto-incrementing ID, a sentence ID, and a global sentence ID to each token. As follows:
Usage:¶
Below is the usage information that can be generated by running corpus_entity_extractor --help.
corpus_entity_extractor --input_csv path/to/csv/file --text_columns "name of the column to be tokenized" --additional_columns "Column3,Column4" --output_csv path/to/csv/file
Options:¶
--input_csv CSV_FILE_PATH
Path of csv file
--text_columns STR
Name of the text column that need to be tagged
-- additional_columns
name of columns that returned as they are
-- output_csv
path to csv file
Examples:¶
corpus_entity_extractor --input_csv "input.csv" --text_columns "TextColumn1" --additional_columns "Column3,Column4" --output_csv "output.csv"