Method, system and storage medium for improving sentence vector semantics
A sentence vector and semantic technology, applied in the field of natural language processing, can solve the problems of not being better, the sentence vector cannot be very accurate, and the expression effect of the sentence vector is not so accurate, so as to achieve the effect of improving the expression effect.
Pending Publication Date: 2019-03-01
XIAMEN KUAISHANGTONG INFORMATION TECH CO LTD
View PDF6 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] In the field of Natural Language Processing (NLP), the sentence vector has not been able to express the meaning of a sentence very accurately, especially the sentence in the context, whose meaning changes according to the context. In different contexts, the sentence The expression effect of the vector is not so accurate, and there has been no better solution in this regard
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
[0029] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0030] Such as figure 1 Shown, a kind of method of promoting sentence vector semantics of the present invention, it comprises the following steps:
[0031] a. Extend the context of the current sentence to obtain the extended text;
[0032] b. performing named entity recognition on the extended text to obtain entity words of the extended text;
[0033] c. performing word segmentation processing on the extended text, and removing the entity words and stop words from the word segmentation results to obtain non-entity words;
[0034] d. Calculate word ve...
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, a system and a storage medium for improving sentence vector semantics. The method includes performing context expansion on a current sentence and obtaining an expanded text; and performing named entity recognition on the extended text to obtain entity words of the extended text; and performing word segmentation processing on the extended text, and removing the entity word and the stop word from the word segmentation result to obtain the non-entity word; then calculating a word vector for the entity word and the non-entity word respectively, and assigning a first weight to the word vector of the entity word and assigning a second weight to the word vector of the non-entity word; Finally, calculating a weighted average value of all the word vectors accordingto the word vectors of the entity word and the non-entity word and corresponding weights as sentence vectors of the current sentence so as to enhance the expression effect of sentence vectors on sentence semantics.
Description
technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method for improving the semantics of sentence vectors and a system and a storage medium for applying the method. Background technique [0002] In the field of Natural Language Processing (NLP), the sentence vector has not been able to express the meaning of a sentence very accurately, especially the sentence in the context, whose meaning changes according to the context. In different contexts, the sentence The expression effect of the vector is not so accurate, and there has been no better solution in this regard. Contents of the invention [0003] In order to solve the above problems, the present invention provides a method, system and storage medium for improving the semantics of sentence vectors. The vector of the current sentence is obtained by increasing the weight of context words, thereby improving the expression effect of sentence vectors on sente...
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 IPC IPC(8): G06F17/27
CPCG06F40/211G06F40/284G06F40/30
Inventor 刘浪肖龙源蔡振华李稀敏刘晓葳谭玉坤王静
Owner XIAMEN KUAISHANGTONG INFORMATION TECH CO LTD