Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Question decomposition type semantic parsing method fusing fact text

A semantic analysis and decomposition technology, applied in the field of natural language processing, can solve the problems of inability to accurately parse the complex semantics of questions, poor performance of the question answering system, wrong judgment of the model, etc., to enhance the recognition accuracy, improve the experimental performance, reduce the The effect of error propagation

Pending Publication Date: 2022-08-02
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is: the present invention provides a question-sentence-decomposed semantic analysis method that integrates factual texts, so as to solve the problem that the model wrongly judges or loses the question sentences in the process of decomposing complex questions into simple question sequences. The problem of subject entities; solves the problem that when the knowledge base question answering technology faces complex questions, the model cannot accurately parse the complex semantics in the question sentences, resulting in poor performance of the question answering system

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
  • Question decomposition type semantic parsing method fusing fact text
  • Question decomposition type semantic parsing method fusing fact text
  • Question decomposition type semantic parsing method fusing fact text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Example 1: as Figure 1-3 As shown in Figure 1, the decomposing semantic parsing method of question sentences fused with factual texts, firstly, the present invention converts the triples in the knowledge base into factual textual information described in natural language, constructs a factual text base, and uses the attention mechanism to obtain Richer knowledge representation as auxiliary information. Secondly, the semantic parsing process of complex questions is divided into three stages. In the first question decomposition stage, the complex question is decomposed into a series of simple sub-question sequences; in the second information extraction stage, the original question and sub-question sequence are analyzed. Information extraction and integration are performed to obtain key information; in the third semantic analysis stage, corresponding structured query statements are generated.

[0052] As a further scheme of the present invention, the concrete steps are 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

No PUM Login to View More

Abstract

The invention relates to a question decomposition type semantic analysis method fusing a fact text, and belongs to the technical field of natural language processing. The method comprises the following steps of: dividing into three stages of decomposition, extraction and analysis, firstly decomposing a complex problem into a simple sub-problem sequence, then extracting key information in an original problem and the sub-problems, and finally generating a structured query statement by integrating the information. Meanwhile, in order to avoid the situation of entity judgment errors or subject entity missing in the decomposition process, triples in the knowledge base are converted into fact text information described by a natural language, a fact text base is constructed, an attention mechanism is adopted to obtain richer knowledge, and the purposes of enhancing entity representation information and reducing error propagation are achieved. According to the method, the fact text information is fused, semantic analysis is carried out on the complex problem by adopting a question decomposition mode, the understanding ability of the question and answer model on the complex problem is improved, and therefore the problem that the processing effect of a knowledge base question and answer technology on the complex problem is poor is solved.

Description

technical field [0001] The invention relates to a decomposing semantic parsing method for question sentences fused with factual texts, and belongs to the technical field of natural language processing. Background technique [0002] Knowledge base question answering technology aims to find answers to questions from pre-established structured knowledge bases, and has become one of the research hotspots in academia and industry due to its wide range of application scenarios and huge application value. With the continuous development of knowledge base construction technology, the scale of knowledge base is getting larger and larger, such as Freebase, DBpedia, Wikidata and other large knowledge bases store a wealth of related knowledge, which provides a data foundation for knowledge base question and answer. [0003] However, most of the current question answering systems can only answer factual questions, cannot handle complex questions well, and are difficult to understand the ...

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 Applications(China)
IPC IPC(8): G06F40/30G06F40/295G06F16/2452
CPCG06F40/30G06F40/295G06F16/24522
Inventor 高盛祥杨玉倩余正涛宋燃
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products