Sentence vector generation method and system oriented to intelligent question-answering system

A technology of intelligent question answering and sentence vector, applied in semantic analysis, instruments, electronic digital data processing, etc., can solve the problems of fusion of words and word semantic relationship information, no further display, etc., to achieve the effect of improving query accuracy

Active Publication Date: 2021-08-13
GUANGZHOU BAILING DATA CO LTD
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current pre-training model mainly generates codes based on the co-occurrence relationship between words and sentences, and does not further clearly integrate the semantic relationship information between words and words, so further improvement and promotion are needed.

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
  • Sentence vector generation method and system oriented to intelligent question-answering system
  • Sentence vector generation method and system oriented to intelligent question-answering system
  • Sentence vector generation method and system oriented to intelligent question-answering system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] In this embodiment, the sentence vector generation method for intelligent question answering system includes the following steps:

[0039] S1. Carry out Chinese word segmentation for a given Chinese sentence;

[0040] Such as figure 1 As shown, given a Chinese sentence, Chinese word segmentation is performed first. Word segmentation is the process of recombining continuous word sequences into word sequences according to certain specifications. Currently there are a lot of open source Chinese word segmentation tools. This embodiment uses the HanLP word segmentation technology to directly and efficiently complete the automatic word segmentation of Chinese sentences.

[0041] For example, the sentence: "He is studying the origin of life", the correct participle result is:

[0042] He / is / studies / the / origin of / life.

[0043] And the wrong participle result is:

[0044] He / is / the / origin of / postgraduate / life / .

[0045] S2. Generate a corresponding Chinese word vector for...

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 sentence vector generation method and system oriented to an intelligent question-answering system. The method comprises the following steps: performing Chinese word segmentation on a given Chinese sentence; generating a corresponding Chinese word vector for each word according to a word segmentation result; performing semantic role labeling on the sentences to generate a semantic relation graph of the sentences; taking word vectors as input, coding sentences, and outputing a hidden state vector of each word vector; encoding the semantic relation graph to generate an adjacent matrix of the semantic relation graph; and inputting the adjacent matrix of the semantic relation graph and the hidden state vector of the word vector into a GCN, and performing layer-by-layer fusion iteration with each output of the middle layer of the BERT pre-training model to obtain a final coded sentence vector. Compared with a general sentence vector generation method, due to the fact that semantic structure codes of sentences are fused in the invention, richer and more instructive information is provided, higher-quality input is provided for similar question semantic matching, and the query precision is improved.

Description

technical field [0001] The invention belongs to natural language processing technology (NLP) in artificial intelligence, and specifically relates to a sentence vector generation method and system for an intelligent question answering system. Background technique [0002] Question-Answering system (Question-Answering) is a research direction that has attracted much attention and has broad application prospects in the field of artificial intelligence and natural language processing. The retrieval-type question-answering system for frequently asked questions (FAQ) is currently the most A widely used intelligent question answering system. FAQ search-type question and answer is based on the query submitted by the user, searches the FAQ database for the closest corresponding question in semantics, and feeds back the corresponding answer to the user. [0003] The core task of the FAQ question answering system can be abstracted as the semantic matching task of similar questions, th...

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): G06F16/332G06F16/33G06F16/338G06F40/211G06F40/289G06F40/30
CPCG06F16/3329G06F16/3344G06F16/338G06F40/211G06F40/289G06F40/30
Inventor 杨钊何慧
Owner GUANGZHOU BAILING DATA CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap