Detection of document similarity

An electronic device comprising:

• a processing unit;
• and
• a memory operatively coupled to the processing unit and that stores computer executable instructions that, based on execution by the processing unit, facilitate performance of acts, comprising:
• identifying a first pragmatic association of a plurality of pragmatic associations of a first segment in a first document portion, wherein the first pragmatic association indicates meaning of the first segment specific to a context of the first segment in the first document portion;
• generating a first intermediate document portion from the first document portion by using the first pragmatic association to replace the first segment;
• determining a first value representation associated with the first document portion and a second value representation associated with a second document portion, wherein the first value representation has a defined number of dimensions corresponding to different pragmatic associations;
• determining a similarity degree between the first document portion and a second document portion by comparing the first intermediate document portion with the second document portion and by comparing the first value and the second value, wherein the first value and the second value are represented as vectors with multiple dimensions of weights and the similarity degree is determined based on calculating a cosine similarity between the two vectors;
• and
• replacing a segment in the first intermediate document portion with a corresponding pragmatic association, wherein the replacing is based on the determining the similarity.

A computer program product for detection of document similarity, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by an electronic device to cause the electronic device to:

• identify, by the electronic device, a first pragmatic association of a first segment in a first document portion, wherein the first pragmatic association indicates meaning of the first segment specific to a context of the first segment in the first document portion;
• generate, by the electronic device, a first intermediate document portion from the first document portion by using the first pragmatic association to replace the first segment;
• determine, by the electronic device, a first value representation associated with the first document portion and a second value representation associated with the second document portion;
• and
• determine, by the electronic device, a similarity degree between the first document portion and the second document portion by comparing the first intermediate document portion with the second document portion and by comparing the first value representation and the second value representation, wherein the first value representation and the second value representation are as vectors with multiple dimensions of weights and the similarity degree is determined based on calculating a cosine similarity between the two vectors and, wherein the first value representation is determined based on a frequency of occurrence of the first pragmatic association and wherein the second value representation is based on a frequency of occurrence of a second pragmatic association for the second document portion.