Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and related equipment for parsing the semantic structure of a sentence

A technology of semantic structure and sentences, applied in the field of human-computer interaction

Active Publication Date: 2019-06-07
深兰人工智能芯片研究院(江苏)有限公司 +2
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a method and related equipment for analyzing the semantic structure of sentences, so as to solve the deficiencies in the existing syntactic analysis research work

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and related equipment for parsing the semantic structure of a sentence
  • A method and related equipment for parsing the semantic structure of a sentence
  • A method and related equipment for parsing the semantic structure of a sentence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0025] figure 1 It is a schematic flow chart of the method for analyzing the semantic structure of sentences provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the method includes:

[0026] Step 101, receiving an input sentence, and performing word segmentation on the sentence according to a word segmentation algorithm, to obtain one or several word segmentation results;

[0027] Step 102, on the basis of the word segmentation results, perform semantic structure analysis to obtain the relationship between the sentence components of the sentence and the internal structure of the sentence components.

[0028] Wherein, the semantic structure analysis is carried out to obtain the relationship between the sentence components of the sentence, including:

[0029] First, identify and mark the time and place components to obtain the free components of the sentence;

[0030] Then, identify and mark the predicate or predicate components to obtain the predic...

Embodiment 1

[0052] Traditional technical solutions mainly give a formal explanation based on the perspective of syntax tree analysis, but the results of syntax tree analysis (in many cases) are not unique. In the embodiment of the present invention, the idea of ​​using "simple sentences" to explain "complex sentences" is adopted, and a new idea of ​​semantic understanding is given. The explanation idea is hierarchical (multiple different levels of understanding can be given) . This idea is easy to understand, and it is practical in human-computer interaction scenarios (especially in dialogue systems and language generation scenarios).

[0053] figure 2 A schematic flow diagram of the method for analyzing the semantic structure of a sentence provided in Embodiment 1 of the present invention, as figure 2 As shown, the method includes:

[0054] Step 201, segmenting the input sentence according to the word segmentation algorithm;

[0055] Among them, any existing mature word segmentatio...

Embodiment 2

[0063] image 3 A schematic flow chart of the method for analyzing the semantic structure of a sentence provided in Embodiment 2 of the present invention, such as image 3 As shown, the method includes:

[0064] Step 301, the text string input of sentence;

[0065] Step 302, word segmentation;

[0066] Among them, any existing mature word segmentation algorithm can be used to segment the sentence (multiple possible word segmentation schemes (structures) are allowed, and subsequent programs can evaluate and screen multiple word segmentation schemes).

[0067] Step 303, sentence component recognition task 1: time and place component recognition and labeling;

[0068] Step 304, sentence component recognition task 2: predicate (predicate) component recognition and labeling;

[0069] Among them, steps 303 and 304 can be fed back to the word segmentation algorithm for recognition results and iteratively perform word segmentation and recognition. In addition, steps 303 and 304 do...

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

No PUM Login to View More

Abstract

The embodiment of the invention relates to the field of human-computer interaction, and discloses a method for analyzing a sentence semantic structure and related equipment. The method comprises the following steps: receiving an input sentence, and carrying out word segmentation on the sentence according to a word segmentation algorithm to obtain one or more word segmentation results; and on the basis of the word segmentation result, carrying out semantic structure analysis to obtain a relationship among sentence components of the sentence and an internal structure of the sentence components.Therefore, the sentence components are used for analyzing the semantic structure of the sentence, and the method can be applied to semantic interpretation and understanding in scenes such as questionsand answers and dialogues of human-computer interaction.

Description

technical field [0001] The embodiments of the present invention relate to the field of human-computer interaction, and in particular to a method and related equipment for analyzing the semantic structure of sentences. Background technique [0002] Semantic understanding is one of the core goals of natural language processing, but the research work on semantic understanding is progressing slowly. The current research ideas on natural language processing and semantic understanding are mainly bottom-up methods, and more mature related research work is mainly on syntactic analysis and semantic role labeling. Among them, the basic task of syntactic analysis (including dependency syntactic analysis) is to determine the syntactic structure of a sentence or the dependency relationship between words in a sentence. Usually according to the given grammatical system, the syntactic structure of the sentence is automatically deduced, and the words or phrases contained in the sentence and...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/332G06F17/27
CPCG06F40/211G06F40/289G06F40/30
Inventor 陈海波
Owner 深兰人工智能芯片研究院(江苏)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com