LSTM neural network training method and device
A neural network training and neural network technology, which is applied in the field of LSTM neural network training methods and devices, can solve the problems of high training calculation overhead and complex Transformer model structure, and achieve the effects of improving carrying capacity, increasing calculation amount, and improving data quality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0040] Example 1
[0041] An LSTM neural network training method includes training data generated from unlabeled text. After processing keywords in the unlabeled text, the training data is weighted according to the keywords to improve the ability of the training data to carry feature information. The training data is used for LSTM neural network training. The present invention draws on the physiological basis of human beings’ focusing on key positions or words when acquiring information, and combines the long and short-term memory network LSTM, and proposes a model training method without changing the model structure, by changing the weight of key information in the training data , To obtain better performance model training results.
Example Embodiment
[0042] Example 2
[0043] The difference between this embodiment and embodiment 1 is that the training data generated from the unlabeled text processes the keywords in the unlabeled text and then weights the training data according to the keywords to improve the ability of the training data to carry feature information. , The method of using weighted training data for LSTM neural network training includes the following steps:
[0044] S1. Use unlabeled text as training text and preprocess the training text;
[0045] S2. Recognize the preprocessed training text and generate keywords for the training text;
[0046] S3. Encode the words in the training text to obtain a high-dimensional space continuous word vector, and perform the same encoding on the keywords to obtain the keyword vector;
[0047] S4. Add the keyword vector to the corresponding word vector to weight the word vector to obtain the final training data;
[0048] S5. Input the final training data into the LSTM neural network f...
Example Embodiment
[0049] Example 3
[0050] The difference between this embodiment and the second embodiment is that the method for preprocessing the training text in step S1 includes at least one of cleaning, word segmentation, and stop word removal.
[0051] Further, the keywords in the step S2 include entity keywords, relationship keywords and event keywords. Perform named entity recognition on the preprocessed training text, obtain common named entities such as name, address, organization, time, currency, quantity, etc., and establish entity keywords. Then extract entity relationships from the preprocessed training text. If there is a relationship between entities, determine whether the entity relationship is a common component and whole, tool usage, member collection, cause and effect, entity destination, content and container, information and theme, production With the types of production and entity and origin, and form a relationship keyword. Event extraction is performed on the preprocessi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap