Question answering method based on machine learning and question and answer model training method and device

Abstract

The invention discloses a question answering method based on machine learning and a question answering model training method and device, and relates to the field of artificial intelligence. The training method comprises the steps of acquiring training samples, each training sample comprising a question sample, an answer sample and a calibration position, and the answer samples being answer documents formed by splicing correct answer samples and wrong answer samples together; encoding the question sample and the answer sample through a question and answer model to obtain a vector sequence of the samples; predicting the position of the correct answer sample in the vector sequence of the sample through the question-answer model, and determining the loss between the position of the correct answer sample and the calibration position; and adjusting model parameters in the question and answer model according to the loss, and training the position prediction capability of the question and answer model for the correct answer sample. According to the method, the spliced answer samples are adopted to train the question and answer model, and the reading understanding ability of the question and answer model is trained, so that the question and answer model can accurately find a correct answer from multiple answers.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a question answering method based on machine learning, a question answering model training method and a device. Background technique [0002] In products such as in-vehicle voice systems, smart speakers, smart customer service, and children's companion robots, the classic question-and-answer model is usually used to implement the question-and-answer function. When the above products collect the questions asked by users, the question answering model can give the most matching answer in the question answering knowledge base. [0003] The question-answer model training method provided by the related art is to use a question-answer pair as input, output a binary classification label, and use the binary classification label to indicate whether the question-answer pair is a positive sample or a negative sample. For example, a question-answer pair <Q, A> is used a...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a machine learning-based question answering method, question answering model training method and device, which can solve the problem that the classic question answering model is easy to give wrong answers when the answers given in the positive samples and negative samples are similar

Images