融入Attention 机制改进Word2vec技术的水利水电工程专业词智能提取与分析方法

Translated title of the contribution: An intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism

Mingchao Li, Dan Tian, Yang Shen, Jonathan Shi, Shuai Han

Research output: Journal article publicationJournal articleAcademic researchpeer-review

6 Citations (Scopus)

Abstract

The traditional text information processing and analysis of hydraulic engineering mainly rely on manual interaction, which exists some problems such as complicated processes, low efficiency, error-prone and so on. In this study, an intelligent and high-efficiency method of professional technical word recognition extraction and analysis is proposed for hydraulic engineering based on the Natural Language Processing (NLP) technology, integrating the Word2vec technique with the attention mechanism. The word vector computing model by the improved Word2vec technology is established. The word vector is used to calculate the similarity between words. The similarity between words serves as a combination standard to extract professional technical words of hydraulic engineering. An intelligent recognition and analysis framework for professional technical words of hydraulic project management is established by professional texts to verify the credibility and realize the automatic extraction accuracy of professional technical words. This approach is applied to analyze the weekly supervision report text of a practical concrete dam construction for 229 weeks. There are 9034 extracted professional technical words after three iterations, and the accuracy is 87.58%. It effectively improves the efficiency, accuracy and intelligence level of text information extraction and analysis of hydraulic engineering.

Translated title of the contributionAn intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism
Original languageChinese (Simplified)
Pages (from-to)816-826
Number of pages11
JournalShuili Xuebao/Journal of Hydraulic Engineering
Volume51
Issue number7
DOIs
Publication statusPublished - 1 Jul 2020

Keywords

  • Attention mechanism
  • Hydraulic engineering
  • Intelligent extraction
  • Natural language processing (NLP)
  • Professional text
  • Word vector
  • Word2vec

ASJC Scopus subject areas

  • Water Science and Technology
  • Energy Engineering and Power Technology
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'An intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism'. Together they form a unique fingerprint.

Cite this