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

Case-related news viewpoint sentence recognition method based on BERT and BiLSTM-Attention

A recognition method and a technology of opinion sentences, which are applied in the field of opinion sentence recognition and neural networks, can solve the problems of complex feature engineering and invisible noise in the opinion sentence recognition method, and achieve the effect of improving classification and recognition effects

Pending Publication Date: 2020-07-10
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to solve the complex feature engineering and invisible noise problems of the traditional opinion sentence recognition method

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
  • Case-related news viewpoint sentence recognition method based on BERT and BiLSTM-Attention
  • Case-related news viewpoint sentence recognition method based on BERT and BiLSTM-Attention
  • Case-related news viewpoint sentence recognition method based on BERT and BiLSTM-Attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0054] Such as figure 1 Shown, the inventive method is divided into six steps:

[0055] Step S1: Input the news text involved in the case, perform preprocessing, perform word segmentation on the text, and remove stop words.

[0056] For example, there is a Chinese sentence sentence1=['I love natural language processing'], sent1=I / love / nature / language / processing after word segmentation.

[0057] Step S2: use BERT to pre-train word vectors, for example, a certain sentence S has a length of n, and S={w 1 ,w 2 ,...w n}, where w i is the i-th word in the sentence S, w i can be mapped to a word vector e i , where 1≤i≤n.

[0058] At the same time, there is a word vector matrix: W∈R d*|V| , where |V| is the vocabulary length and d is the word vector dimension.

[0059] Get the word vector corresponding to each word through the word vector ma...

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 a case-related news viewpoint sentence recognition method based on BERT and a BiLSTM-Attention model, and the method comprises the steps: firstly, carrying out the preprocessing of a news text, including word segmentation and duplication removal; then, coding words in the text into vectors through BERT to obtain text features, and coding case elements corresponding to all sentences into vectors to obtain case information; splicing the feature vectors, and inputting the spliced feature vectors into the BiLSTM to obtain past and future features and time sequence information; enabling the output of the layer to be related to case elements through Attention to pay attention to important information, and finally judging whether sentences are viewpoint sentences or not through a softmax classifier. According to the method, BiLSTM is added, so more sentence semantic information can be obtained. Meanwhile, case elements are fused to obtain more case domain information,an Attention mechanism is introduced to associate the case elements, and more important information for a viewpoint sentence recognition task is paid attention to. The word vector generated by using the BERT is dynamic, and compared with a general word2vec word vector, the word vector generated by using the BERT can solve the problem of one word with multiple meanings.

Description

technical field [0001] The invention relates to the field of opinion sentence recognition and neural network technology, in particular to a method for recognizing opinion sentences in case-related news based on BERT and BiLSTM-Attention models. Background technique [0002] Case public opinion refers to the network public opinion related to the case. Analyzing the news related to the case can obtain relevant public opinion information, which plays an important role in preventing and solving the public opinion risks caused by it. Among them, the recognition of opinion sentences is mainly used to analyze the emotional polarity of news texts, which can help to obtain relevant public opinion information. Therefore, the focus of the present invention is how to identify opinion sentences from case-related news texts. [0003] General opinion sentences refer to those sentences that contain opinions, and these sentences generally include emotional words and trigger words. And 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
IPC IPC(8): G06F40/289G06F40/284G06F40/30G06F40/126G06F16/35
CPCG06F16/355
Inventor 黄彪李涛
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com