Method for determining statement smoothness and method and device for determining probability prediction model
A probability prediction and probability model technology, applied in natural language processing and artificial intelligence fields, can solve problems such as poor generalization and detection results limited by word segmentation quality
Pending Publication Date: 2021-02-19
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In related technologies, the model for detecting fluency of sentences is usually based on the principle of word frequency, which has the disadvantages of poor generalization and detection results are limited by word segmentation quality
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0025] The present application provides a method for determining the fluency of a sentence. The method first obtains the sentence to be processed. Then, word segmentation processing is performed on the sentence to be processed to obtain the first character sequence; and word segmentation processing is performed on the sentence to be processed to obtain the first word...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for determining statement smoothness and a method and device for determining a probability prediction model. The method can be applied to the fields of natural language processing and deep learning. According to the specific implementation scheme, the method for determining statement smoothness comprises the steps of obtaining a to-be-processed statement; carryingout word segmentation processing on the to-be-processed statement to obtain a first character sequence; performing word segmentation processing on the to-be-processed statement to obtain a first wordsequence; adopting a pre-trained probability prediction model to determine a first probability that a target character in the first character sequence appears in the to-be-processed statement, and determining a second probability that a target word in the first word sequence appears in the to-be-processed statement; and determining the smoothness of the to-be-processed statement according to the first probability and the second probability.
Description
technical field [0001] The present application relates to the field of artificial intelligence, specifically to the fields of natural language processing and deep learning, and more specifically to a method and device for determining the fluency of a sentence, a method and device for determining a probability prediction model, a device, and a storage medium. Background technique [0002] In the text generation scenario, when using text recognition software to extract text from pictures, there are often recognition errors and missing information, and the sentences generated by the text generation strategy have limitations and may not be high-quality and usable. In order to improve the quality of the generated sentences, the smoothness of the sentences can be checked, and high-quality sentences can be selected from the generated text. [0003] In related technologies, the model for detecting fluency of sentences is usually based on the principle of word frequency, which has th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/284G06F40/216
CPCG06F40/284G06F40/216
Inventor 念天磊刘丽韩友郑立涛
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD