SUMMA First Sentence Similarity

Functionality

Computes the similarity of each sentence to the first sentence of the document. Consider the vectors associated to the sentences for computing the similarity in terms of the cosine formula. The feature is stored in each sentence with name 'first_sim'.

Parameters of the Resource

• annSetName: the annotation set where the annotations live
• sentAnn: the name of the sentence annotation.
• vecAnn: the name of the vector associated to the sentence.

Restriction

None. But to obtain the desired behaviour you should have sentences and vectors computed.