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

User comment attribute extraction method based on bi-directional dependency syntactic tree representation

A technology that relies on grammar and user comments, applied in the field of computer natural language processing, can solve problems such as staying

Active Publication Date: 2018-08-03
SOUTHWEST JIAOTONG UNIV
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing deep learning algorithms used in user comment attribute extraction tasks only focus on the extraction of text sequence features and shallow-level dependent features, and the application of deep-level dependent feature extraction and fusion of sequence features and dependent features. There are still a lot of deficiencies

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
  • User comment attribute extraction method based on bi-directional dependency syntactic tree representation
  • User comment attribute extraction method based on bi-directional dependency syntactic tree representation
  • User comment attribute extraction method based on bi-directional dependency syntactic tree representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0061] Step 1: Preprocess the user comment text in a specific field, and then segment sentences and words to obtain the word segmentation sequence; finally construct a grammatical dependency tree for the word segmentation sequence;

[0062] Step 1.1: Preprocessing the user comment text.

[0063] Step 1.2: Use natural language processing tools to segment and word-segment the preprocessed text sequence, and obtain the word-segmentation sequence S={w 1 ,w 2 ,...,w i ,...,w N}, where N is the matrix sequence length, w i For the words that make up the comment text; then the word segmentation sequence and the corresponding label sequence L={t 1 ,t 2 ,...,t i ,...,t N} for statistics and numbering, and construct corresponding vocabulary V and label table T={B-AP, I-AP, O}, wherein B-AP represents the beginning word of the comment attribute,...

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 user comment attribute extraction method based on bi-directional dependency syntactic tree representation. The method comprises the steps that 1) given user comment text is preprocessed, and a dependency syntactic tree is generated; 2) a bi-directional dependency syntactic tree representation network is established, and dependency characteristics among words are extracted; 3) the dependency characteristics are input into a bi-directional LSTM nerve network, sequence characteristics among the words are extracted on the basis of the dependency characteristics, and accordingly the dependency characteristics are effectively combined with the sequence characteristics; 4) the combined characteristics are coded by using a linear chain condition random field; 5) a Viterbialgorithm is used for conducting decoding to obtain comment attributes of all text. According to the user comment attribute extraction method, the aim is effectively achieved that in user comment attribute extraction tasks, the dependency characteristics of text syntax are extracted and efficiently combined with the sequence characteristics to achieve end-to-end training; the condition random field is used for coding the combined characteristics, the Viterbi algorithm is used for decoding the combined characteristics, and the good effect can be achieved in the user comment attribute extraction tasks.

Description

technical field [0001] The invention relates to the technical field of computer natural language processing, in particular to a user comment attribute extraction method based on bidirectional dependency syntax tree representation. Background technique [0002] The life of modern people is increasingly inseparable from the Internet. In the Internet environment, people are constantly expressing and expressing their own views and emotions to people or things. Especially in the online shopping and catering industry, being able to evaluate goods and services objectively or subjectively is the appeal of almost every participant, which leads to the continuous generation of a large number of user comment texts. How to dig out useful information for merchants and users from a huge amount of review data is a problem that review opinion mining technology needs to deal with. In the past research work, no matter whether it is to classify the sentiment of the user's entire review text, ...

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): G06F17/27G06F17/22G06N3/04G06N3/08
CPCG06F40/154G06F40/279G06N3/049G06N3/084
Inventor 李天瑞罗怀芍王斌
Owner SOUTHWEST JIAOTONG UNIV
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