An example extension method, device, equipment and medium
An extension method and random seed technology, applied in text database query, unstructured text data retrieval, etc., can solve the problems of single sentence pattern in extended examples, limited training improvement of sequence annotation model, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] figure 1 It is a flow chart of an example extension method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of performing instance expansion based on a small number of provided instances. The method can be executed by an example extension device, and the device can be realized by software and / or hardware. see figure 1 , the instance extension methods provided in this embodiment include:
[0048] S110. Obtain instance rules to be expanded including keyword information.
[0049] Wherein, the keyword information may be any information describing the extended instance. The instance-to-be-extended rule is used to limit any part of the extended instance. Specifically, the keyword information may be a keyword or a relationship between keywords. Typically, the keyword information may be at least one of text intent, slot, and slot sequence.
[0050] Exemplarily, the instance rule to be extended may be: "from" is followed by a st...
Embodiment 2
[0067] figure 2 It is a flow chart of an example extension method provided by Embodiment 2 of the present invention. This embodiment is an optional solution proposed on the basis of the foregoing embodiments. see figure 2 , the instance extension methods provided in this embodiment include:
[0068] S210. Determine the instance rule to be extended associated with the instance to be extended.
[0069] Specifically, the rules for determining the instance to be extended associated with the instance to be extended include:
[0070] Perform text analysis on the instance to be extended, and extract instance rules to be extended from the instance to be extended according to the text analysis result.
[0071] The determination of the above instance rules to be extended can achieve the following effects: only according to a small number of instances to be extended provided by the user, an instance extension model that meets the needs of the user can be trained.
[0072] However,...
Embodiment 3
[0085] Figure 3a It is a flow chart of an example extension method provided by Embodiment 3 of the present invention. This embodiment is an optional solution proposed on the basis of the foregoing embodiments. see Figure 3a , the instance extension methods provided in this embodiment include:
[0086] Offline model generation and online instance generation.
[0087] Specifically, see Figure 3b , offline model generation includes:
[0088] Extract several instances to be expanded from the database that stores a large amount of data;
[0089] Extract a number of instance rules to be extended from the instance to be extended;
[0090] Wherein, the instance rules to be expanded include keywords or relationships between keywords, for example, keyword A must be before keyword B.
[0091] A to-be-extended instance rule and an to-be-extended instance conforming to the to-be-extended instance rule are used as a pair of training samples, put into a machine learning model for t...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More