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

Statement similarity judgment method and judgment system

A similarity and sentence technology, applied in the field of sentence similarity judgment method and judgment system, can solve the problem that the model cannot learn interactive information of different granularities

Active Publication Date: 2020-09-11
CHONGQING UNIV
View PDF14 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both word granularity and multi-granularity interaction are artificially specified in the granularity of interaction, which may cause the model to be unable to learn real interaction information of different granularities

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
  • Statement similarity judgment method and judgment system
  • Statement similarity judgment method and judgment system
  • Statement similarity judgment method and judgment system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0048] A sentence similarity judgment method, comprising the following steps,

[0049] Step 1: Context information modeling;

[0050] Use BiLSTM as the sentence encoding layer; BiLSTM uses word embedding as input, assuming that the dimension of the pre-trained word embedding is d, and the lengths of the input sentence pairs S and T are ls and lt respectively, then S and T correspond to an input matrix respectively S=[S 1 ,S 2 ,...,S ls ], T=[T 1 , T 2 ,...,T lt ], S i and T j represent the d-dimensional word embeddings of the i-th word in S and the j-th word in T, respectively, assuming that the dimension of the LSTM hidden layer is u, given the word embedding x of the t-th time step t , the hidden layer output h of the previous time step t-1 and cell state c t-1 , LSTM obtains the output of the tth time step as follows:

[0051] i t =σ(w xi x ...

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 statement similarity judgment method and judgment system, and relates to the technical field of natural language semantic similarity calculation. Improvements are performed on a modeling layer, a multi-semantic embedding layer, a semantic importance calculation layer, a semantic alignment layer and an output layer, a multi-granularity level similarity matrix is calculatedby utilizing the multi-semantic matrix, and true semantic alignment of the two sentences is discovered according to the matrix. The fact that different semantics have different importance is considered, and semantic importance calculation is provided. The proposed model does not need sparse features, WordNet and other external resources, is successfully trained in a short time, and obtains a competitive result on a similarity calculation task. Visual analysis shows that the model has good performance and interpretability.

Description

technical field [0001] The invention relates to the technical field of natural language semantic similarity calculation, more specifically, it relates to a sentence similarity judgment method and judgment system. Background technique [0002] Many scenarios in life need to compare text similarities, such as plagiarism detection, dialogue systems, and information retrieval. Therefore, how to quickly and visually detect the similarity of sentences is a basic and very important task. [0003] Sentence pair semantic matching (SPSM) is the most fundamental problem in NLP, such as text similarity detection, natural language inference, paraphrase recognition, answer selection, etc. With the renaissance of neural networks in fields such as NLP, researchers began to work on using neural networks to solve SPSM tasks. Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been proficiently applied to SPSM tasks. A lot of previous work has dealt with the semanti...

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): G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F40/30G06N3/049G06N3/08G06N3/045G06F18/22G06F18/2415Y02D10/00
Inventor 朱晓红陈俊宇何胜冬
Owner CHONGQING 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

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