Automatic question-answering method based on deep learning

A technology of automatic question answering and deep learning, applied in neural learning methods, natural language data processing, special data processing applications, etc., can solve problems such as inability to truly understand text semantics, semantic gaps, etc., to reduce system development costs and improve relevance , the effect of narrowing the range

Inactive Publication Date: 2018-07-31
ZHEJIANG UNIV
View PDF3 Cites 48 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In question retrieval, similarity calculation methods such as BM25 and TFIDF based on character coincidence are

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
  • Automatic question-answering method based on deep learning
  • Automatic question-answering method based on deep learning
  • Automatic question-answering method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] When a user asks the question "Can ginger cure hair loss", the processing flow of the system is described as follows:

[0054] 1) Use the Elasticsearch full-text search service to select 500 similar questions from the system database, and the 500 questions obtained are all questions that contain common words with the user's questions.

[0055] 2) Use the Jieba word segmentation tool for Chinese word segmentation, set a user-defined dictionary in the Jieba tool, enable stop word removal, and the question after word segmentation is "ginger | treatment | hair loss".

[0056] 3) Calculate the TFIDF of each word in the user question and similar questions.

[0057] 4) Use the BOW vector, TFIDF and Word2Vec model in the construction stage to construct a 200-dimensional text representation vector for user questions and similar questions, where the word vector obtained according to the Word2Vec model is as follows: figure 2 As shown, each word is converted into a 200-dimension...

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 discloses an automatic question-answering method based on deep learning, and aims to provide an algorithm-based fully-automatic question-answering scheme for a user. According to the method, question and answer pairs crawled from websites are used as data sources, and questions with more complicated forms can be answered. According to the method, on the basis of traditional similar-question retrieval, a BOW model, a TFIDF model and a Word2Vec model are utilized to represent text contents of questions as vectors, similar questions are resorted and screened out through calculatingsimilarity between vectors, semantic knowledge can be introduced, the semantic gulf problem in traditional question retrieval processes can be solved, and validity of candidate answers can be improved. In addition, based on deep learning, the method utilizes a neural network model, which is obtained by training, for matching scoring on a question and the candidate answers, and can automatically extract high-layer matching features between the question and the answers, automatically give an answer of the question, improve accuracy of an automatic question-answering system, reduce manual intervention at the same time, and reduce system development costs.

Description

technical field [0001] The invention relates to the fields of information retrieval, text representation method, text similarity calculation, and automatic question answering in the field of natural language processing, and specifically relates to an automatic question answering method based on deep learning. Background technique [0002] With the rapid development of the Internet, a large number of electronic documents appear on the Internet. When users are looking for an answer to a question, traditional information retrieval cannot directly give the answer, but can only give thousands of webpage links, so it can automatically The automatic question answering technology that gives the best answer is getting more and more attention. The research on automatic question answering methods is mainly divided into template matching methods, information retrieval methods and deep learning methods. [0003] The method based on template matching needs to manually write a large numbe...

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
IPC IPC(8): G06F17/27G06F17/30G06N3/08
CPCG06F16/3329G06F40/289G06F40/30G06N3/084
Inventor 张引张扬扬金哲
Owner ZHEJIANG UNIV
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