Complementary evidence identification in natural language inference

A non-transitory computer readable medium comprising computer executable instructions which when executed by a computer cause the computer to perform the method of:

• obtaining a given question q;
• obtaining a set of N passages from an electronic database;
• determining for each passage of the set of N passages, a probability of a corresponding passage being a supportive passage for the given question;
• ranking the set of N passages based on the determined probabilities;
• selecting M passages that are ranked 1 to M of the set of N passages;
• selecting a set of L passages based on a plurality of scores, each score assigned to a set of candidate passages of the set of N passages, each score being based on the determined probabilities, the selected M passages, and a weighted regulation parameter;
• and
• providing a set of M highest ranked passages of the set of L passages to a computerized machine learning system in order to answer the question based on the set of L passages.

An apparatus comprising:

• a memory;
• and
• at least one processor, coupled to said memory, and operative to perform operations comprising:
• obtaining a given question;
• obtaining a set of N passages from an electronic database;
• determining for each passage of the set of N passages, a probability of a corresponding passage being a supportive passage for the given question;
• ranking the set of N passages based on the determined probabilities;
• selecting M passages that are ranked 1 to M of the set of N passages;
• selecting a set of L passages based on a plurality of scores, each score assigned to a set of candidate passages of the set of N passages, each score being based on the determined probabilities, the selected M passages, and a weighted regulation parameter;
• and
• providing a set of M highest ranked passages of the set of L passages to a computerized machine learning system in order to answer the question based on the set of L passages.