Word vector learning model training method and server

A technology of learning models and training methods, applied in the field of machine learning, which can solve the problems that have nothing to do with the smallest semantic unit of words—sememe, and cannot fully express the semantic information of words
CN107239443AInactive Publication Date: 2017-10-10TSINGHUA UNIV
3 Cites 30 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
TSINGHUA UNIV
Publication Date
2017-10-10
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

Embodiments of the invention provide a word vector learning model training method and a server. The method comprises the following steps of: obtaining a word meaning vector and a primitive vector corresponding to a word in a training sample text; expressing a word vector in the training sample text according to the word meaning vector or the primitive vector; and substituting the word vector expressed by the word meaning vector or the primitive vector into an existing word vector learning model and carrying out model training. The server is used for executing above method. According to the word vector learning model training method and the server provided by the invention, the word vector is expressed through the primitive vector or the word meaning vector, and the word vector learning model corresponding to the word vector expressed by the word meaning vector or the primitive vector is trained, so that the semantic information of the word can be sufficiently expressed.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The embodiment of the present invention relates to the technical field of machine learning, and in particular to a training method and server for a word vector learning model. Background technique

[0002] A sememe is the smallest semantic unit of a word, and a limited number of sememes can be used to describe the semantics of a large number of Chinese words. For each word, the sememe possessed by the word is not intuitively displayed. In order to conduct corresponding research, some researchers have manually marked each word, and assigned a word to each word through linguistic knowledge. or multiple sememes, and thus form a knowledge base HowNet (HowNet).

[0003] Word vector refers to the vectorization of words. Word vectors include different dimensions. Each dimension describes a feature of a word. Converting words into word vectors can help computers understand natural language. The existing technology uses word The vector learning model is train...

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