Dynamic reasoning network system and method for multi-hop question answering

Abstract

The present invention provides a dynamic reasoning network and method for multi-hop question answering. The network includes: a paragraph selector, which receives paragraphs and questions, and selects sub-paragraphs related to the answer of the question in the paragraph; a coding module, which uses collaborative attention to strengthen The interaction between questions and sub-paragraphs calculates the final vector representation of sub-paragraphs and the vector representation of questions; the entity graph construction module is used to construct an entity graph; the dynamic reasoning module is used to reason about entity graphs and repeatedly read text imitation The process of human analyzing information, and constructing a question reshaping mechanism to repeatedly read the question and its relevant important parts; the answer prediction module, connected to the encoding module, and connected to the dynamic reasoning module, for receiving the final vector representation of the subparagraph, And the output gets four types of predictions. The network builds a question reshaping mechanism that reads questions repeatedly to imitate people's reading habits and improves the comprehension and reasoning abilities of multi-hop reasoning question answering models.

Description

technical field [0001] The invention belongs to the field of machine reading comprehension, and in particular relates to a dynamic reasoning network and method for multi-hop question answering. Background technique [0002] Machine reading comprehension is a task that obtains the correct answer to a given question by reasoning over a set of texts, while multi-hop reasoning question answering is a subtask of machine reading comprehension that aims to find the answer to a given question across multiple passages; Most current multi-hop reasoning question answering models usually obtain answers by visiting the question only once, so the model may not be able to obtain enough textual information. [0003] The multi-hop reasoning question answering model mainly has three research directions. The first one is based on the memory network, which uses the memory unit to combine the question with the information obtained in each round, and through continuous iterative reasoning after s...

AI Technical Summary

Problems solved by technology

[0004] So far, the above three models have achieved some success, but there are still some limitations; first, most existing models directly reason in all given passages without passage selection to remove interfering passages, which increases the the amount of data processed; second, after existing models encode each text into a representation vector, each text is always rarely accessed, whether it is a question or a paragraph

And the model may not be able to obtain enough information by accessing the text only once or twice, which leads to the underutilization of text information

Images