logitorch.utilities.discourse_delimiter

Attributes

Classes

DiscourseDelimiter

A class that provides methods to split a passage into educational units (EDUs) based on explicit connectives and punctuation delimiters.

Module Contents

class logitorch.utilities.discourse_delimiter.DiscourseDelimiter[source]

A class that provides methods to split a passage into educational units (EDUs) based on explicit connectives and punctuation delimiters.

split_edu(passage: str) str[source]

Splits the passage into educational units (EDUs) by replacing explicit connectives with “<CONNECTIVE>” and punctuation delimiters with “<PUNCT>”.

Args:

passage (str): The passage to be split into EDUs.

Returns:

str: The passage with explicit connectives and punctuation delimiters replaced by “<CONNECTIVE>” and “<PUNCT>” respectively.

split_explicit_connectives(passage: str) List[str][source]

Splits the passage into segments based on explicit connectives.

Args:

passage (str): The passage to be split.

Returns:

List[str]: A list of segments split based on explicit connectives.

split_punctuation_delimiters(passage: str) List[str][source]

Splits the passage into segments based on punctuation delimiters.

Args:

passage (str): The passage to be split.

Returns:

List[str]: A list of segments split based on punctuation delimiters.

regex_explicit_connectives = ''[source]
regex_punctuation_delimiters = ''[source]
logitorch.utilities.discourse_delimiter.EXCPLICIT_CONNECTIVES[source]
logitorch.utilities.discourse_delimiter.PUNCTUATION_DELIMETERS[source]
logitorch.utilities.discourse_delimiter.d[source]