Text implication recognition method fusing high-level semantic information and low-level semantic information
A semantic information and recognition method technology, applied in the field of text implication recognition that integrates high-level and low-level semantic information, can solve problems such as not being very good, and achieve the effects of improving efficiency and accuracy, reducing difficulty, and good generalization
Active Publication Date: 2022-01-07
YANBIAN UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The main reason is that most model methods can only understand the superficial meaning of the text, and the deeper meaning, such as the part involving reasoning, is not very good.
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
[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0047] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0048] Such as figure 1 As shown, the present invention provides a text implication recognition method that integrates high-level and low-level semantic information, including: S1, using pre-trained word vectors a...
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 text implication recognition method fusing high-level semantic information and low-level semantic information. The method comprises the following steps of: S1, processing by adopting a pre-trained word vector and a character-level word vector to obtain a sample set; S2, training the sample set to obtain low-layer semantic information; S3, performing bidirectional attention mechanism processing on the low-level semantic information, and calculating self-attention of the low-level semantic information to obtain high-level semantic information; and S4, fusing the low-level semantic information and the high-level semantic information to obtain fused semantic information, and classifying the fused semantic information through using a convolutional neural network. According to the text implication recognition method, the difficulty of text implication recognition can be reduced, so that text implication recognition is no longer text surface meaning recognition, and the efficiency and the accuracy of text implication recognition are greatly improved.
Description
technical field [0001] The invention relates to the field of natural language processing in computer intelligent information processing, in particular to a text implication recognition method that integrates high-level and low-level semantic information. Background technique [0002] Natural language reasoning is one of the high-level tasks in natural language processing, including machine translation, question answering systems, reading comprehension, and textual implication recognition. Recognizing Textual Entailment (RTE) was proposed by Dagan. It is a problem of studying the relationship between premises and assumptions, mainly including implication, contradiction and neutrality. [0003] Text entailment recognition methods mainly include the following: similarity-based methods, rule-based methods, etc. Since these methods cannot extract the semantic information of sentences very well, their recognition performance is not ideal. In recent years, deep learning-based met...
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): G06F16/35G06F40/30G06K9/62
CPCG06F16/35G06F40/30G06F18/22
Inventor 赵亚慧姜克鑫崔荣一金晶李飞雨高君龙崔东虎王苑茹夏明会刘帆鲁雅鑫赵晓辉
Owner YANBIAN UNIV