kindred.Sentence

class kindred.Sentence(text, tokens, dependencies, sourceFilename=None)

Set of tokens for a sentence after parsing

Variables:

• text – Text of the sentence
• tokens – List of tokens in sentence
• dependencies – List of dependencies from dependency path. Should be a list of tuples with form (tokenindex1,tokenindex2,dependency_type)
• sourceFilename – Filename of the source document
• entityAnnotations – List of entities associated with token indices

Methods

__init__(text, tokens, dependencies, sourceFilename=None)

Constructor for Sentence class

Parameters:

• text (str) – Text of the sentence
• tokens (list of kindred.Token) – List of tokens in sentence
• dependencies (list of tuples) – List of dependencies from dependency path. Should be a list of tuples with form (tokenindex1,tokenindex2,dependency_type)
• sourceFilename (str) – Filename of the source document

addEntityAnnotation(entity, tokenIndices)

Add an entity annotation to this sentence. Associated a specific entity with the indices of specific tokens

Parameters:

• entity (kindred.Entity) – Entity to add to sentence
• tokenIndices (List of ints) – List of token indices

extractMinSubgraphContainingNodes(minSet)

Find the minimum subgraph of the dependency graph that contains the provided set of nodes. Useful for finding dependency-path like structures

Parameters:minSet (List of ints) – List of token indices Returns:All the nodes and edges in the minimal subgraph Return type:Tuple of nodes,edges where nodes is a list of token indices, and edges are the associated dependency edges between those tokens