System for entity and evidence-guided relation prediction and method of using the same

A method comprising:

• providing, by a computing device, a head entity and a document containing the head entity;
• processing, by a language model stored in the computing device, the head entity and the document to obtain head extraction corresponding to the head entity, tail extraction corresponding to tail entities in the document, and sentence extraction corresponding to sentences in the document;
• predicting, by a first bilinear layer stored in the computing device, a head-tail relation between the head extraction and the tail extraction;
• combining, by a second bilinear layer stored in the computing device, the sentence extraction and a relation vector corresponding to the head extraction and the tail extraction, to obtain a sentence-relation combination;
• and
• predicting, by a third bilinear layer stored in the computing device, an evidence sentence from the document based on the sentence-relation combination and attention extracted from the language model, wherein the evidence sentence supports the head tail relation;
• updating parameters of the language model and the first, second and third bilinear layers based on the predicted head entity-tail entity relation, the predicted evidence sentence, and labels of the document containing true head entity-tail entity relation and true evidence sentence.

A non-transitory computer readable medium storing computer executable code, wherein the computer executable code, when executed at a processor of an active computing device, is configured to:

• provide a head entity and a document containing the head entity;
• process the head entity and the document by a language model to obtain head extraction corresponding to the head entity, tail extractions corresponding to tail entities in the document, and sentence extraction corresponding to sentences in the document;
• predict a head entity-tail entity relation between the head extraction and the tail extractions using a first bilinear layer;
• combine the sentence extraction and a relation vector corresponding to the head extraction and the tail extraction using a second bilinear layer to obtain a sentence-relation combination;
• predict an evidence sentence from the document using a third bilinear layer based on the sentence-relation combination and attention extracted from the language model, wherein the evidence sentence supports the head-tail relation;
• and
• update parameters of the language model and the first, second and third bilinear layers based on the predicted head entity-tail entity relation, the predicted evidence sentence, and labels of the document containing true head entity-tail entity relation and true evidence sentence.