SUMMA Sentence Sentence Similarity

Functionality

Adds to each sentence two features ('sim_for' and 'sim_back') representing the similarity of the sentence to the following and previous sentences. The value of the features are the cosines between the vectors of the current sentence and the previous and following sentence.

Parameters of the Resource

• annSet: the annotation set where the annotations live
• sentAnn: the name of the annotation for which you want to compute the feature (e.g. Sentence)
• vecAnn: the name of the annotation for the sentence vector.

Restriction

None. But to obtain the desired functionality you need sentences and vectors previously computed.