Question answer acquisition method and system based on machine reading understanding

Abstract

The embodiment of the invention provides a question answer acquisition method and system based on machine reading understanding. The method comprises the following steps: inputting a question and a corresponding document set into a trained neural network model, and obtaining an output result of the trained neural network model; determining an answer corresponding to the question from the documentset according to the output result; wherein the trained neural network model is obtained through training according to a training set, and the training set comprises a plurality of sample problems anda sample document set and a sample label set corresponding to each sample problem. According to the method and the system provided by the embodiment of the invention, the question and the corresponding document set are input into the trained neural network model, and the answer corresponding to the question is determined from the document set according to the output result of the trained neural network model. The method has the advantages that the shortage of a machine reading understanding model of the description type problem is filled, the characteristics of multiple documents are effectively utilized, more document information is reserved, and the answer of the description type problem can be extracted more accurately.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method and system for obtaining answers to questions based on machine reading comprehension. Background technique [0002] Machine reading comprehension is to give a piece of material and questions to the neural network model, and let the model give the correct answer. According to the existing reading comprehension datasets, in terms of form, the questions can be divided into cloze questions, multiple choice questions, and question-and-answer questions. According to the length of the answers in the data set, the question-and-answer questions can be divided into YesNo questions, simple factual (entity, phrase) questions, and descriptive questions. Aiming at cloze problems and simple practical problems, many neural network models have been proposed to solve the above two types of problems, but there are few studies on description problems. That is, the answ...

AI Technical Summary

Problems solved by technology

That is, it is impossible to obtain answers to descriptive questions through the neural network model in the prior art

Images