Method and apparatus for training machine reading comprehension model, and storage medium
AssigneeBeijing Baidu Netcom Science Technology Co., Ltd.
InventorsKai LIU, Qiaoqiao SHE
Life of this patent
Estimating the term…
Abstract
Embodiments of the present disclosure provide a method and an apparatus for training a machine reading comprehension model, and a storage medium. The method includes: training an initial model to generate an intermediate model based on sample data; extracting samples to be processed from the sample data according to a first preset rule; generating a noise text according to a preset noise generation method; adding the noise text to each of the samples to be processed respectively to generate noise samples; and performing correction training on the intermediate model based on the noise samples to generate the machine reading comprehension model.
Claims17
A method for training a machine reading comprehension model, comprising:
- training an initial model to generate an intermediate model based on sample data;
- extracting samples to be processed from the sample data according to a first preset rule;
- generating a noise text according to a preset noise generation method;
- adding the noise text to each of the samples to be processed respectively to generate noise samples;
- and
- performing correction training on the intermediate model based on the noise samples to generate the machine reading comprehension model.
An apparatus for training a machine reading comprehension model, comprising:
- one or more processors;
- a memory storing instructions executable by the one or more processors;
- wherein the one or more processors are configured to:
- train an initial model to generate an intermediate model based on sample data;
- extract samples to be processed from the sample data according to a first preset rule;
- generate a noise text according to a preset noise generation method;
- add the noise text to each of the samples to be processed respectively to generate noise samples;
- and
- perform correction training on the intermediate model based on the noise samples to generate the machine reading comprehension model.
A non-transitory computer-readable storage medium storing computer instructions, wherein when the computer instructions are executed, the computer is caused to implement a method for training a machine reading comprehension model, and the method comprises:
- training an initial model to generate an intermediate model based on sample data;
- extracting samples to be processed from the sample data according to a first preset rule;
- generating a noise text according to a preset noise generation method;
- adding the noise text to each of the samples to be processed respectively to generate noise samples;
- and
- performing correction training on the intermediate model based on the noise samples to generate the machine reading comprehension model.
Dependencies are inferred from the claim text.