Proximity information retrieval boost method for medical knowledge question answering systems

A device, comprising:

• at least one memory configured to store program code;
• at least one processor configured to read the program code and operate as instructed by the program code, the program code including:
• receiving code configured to cause the at least one processor to receive a first sentence including a first set of words, and receive a second sentence including a second set of words;
• generating code configured to cause the at least one processor to generate, using a word embedding model, a first set of vectors corresponding to the first set of words of the first sentence, generate, using the word embedding model, a second set of vectors corresponding to the second set of words of the second sentence;
• determining code configured to cause the at least one processor to determine a cosine similarity of words of the first sentence and the second sentence, based on the first set of vectors and the second set of vectors, and determine a string similarity between the first sentence and the second sentence by computing a Needleman-Wunsch matrix, based on the first set of vectors, the second set of vectors, and the cosine similarity, the computed Needleman-Wunsch matrix holding alignment scores for alignments of the first set of vector and the second set of vectors, the string similarity being based on the alignment scores;
• and
• transmitting code configured to cause the at least one processor to transmit the string similarity to permit the information retrieval.

A non-transitory computer-readable medium storing instructions, the instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to at least:
• receive a first sentence including a first set of words;
• receive a second sentence including a second set of words;
• generate, using a word embedding model, a first set of vectors corresponding to the first set of words of the first sentence;
• determine a cosine similarity of words of the first sentence and the second sentence, based on the first set of vectors and the second set of vectors;
• determine a string similarity between the first sentence and the second sentence by computing a Needleman-Wunsch matrix, based on the first set of vectors, the second set of vectors, and the cosine similarity, the computed Needleman-Wunsch matrix holding alignment scores for alignments of the first set of vector and the second set of vectors, the string similarity being based on the alignment scores;
• and
• transmit the string similarity to permit the information retrieval.