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

Irony Detection Method Based on Intra-sentence Word Pair Relationship and Contextual User Features

A technology of user characteristics and context, applied in the field of sentiment classification, can solve problems such as sentence inconsistency and inability to capture long-distance dependencies

Active Publication Date: 2020-01-14
HANGZHOU DIANZI UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It not only solves the problem that LSTM sequence modeling cannot capture long-distance dependencies, but also highlights the incongruity within the sentence

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
  • Irony Detection Method Based on Intra-sentence Word Pair Relationship and Contextual User Features
  • Irony Detection Method Based on Intra-sentence Word Pair Relationship and Contextual User Features
  • Irony Detection Method Based on Intra-sentence Word Pair Relationship and Contextual User Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described below in conjunction with the accompanying drawings.

[0022] refer to figure 1 , figure 2 , image 3 , Figure 4 and Figure 5 , an irony detection method based on intra-sentence word-pair relations and contextual user characteristics, including the following steps:

[0023] Step 1. Preprocess the comment text that needs irony detection:

[0024] 1.1. Delete words that appear only once in the entire corpus and replace them with UNK tags;

[0025] 1.2. Delete comments with less than 5 words;

[0026] 1.3. Use the W2V word vector model to represent each comment as a column of word vectors no i is the sentence length.

[0027] Step 2. Use the self-attention mechanism to model the association of each word to obtain the intra-sentence attention representation:

[0028] 2.1 pair input sequence Each word in models the relationship (between words): in, is a parameter that needs to be learned through training. ...

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 irony detection method based on the relationship between word pairs in a sentence and the characteristics of contextual users. The present invention uses a self-attention mechanism (also known as an internal attention mechanism) to analyze word pairs with contradictory emotional polarities in the text. User embeddings are obtained by learning and fusing the user's writing style features and personality features as context information for irony detection. At the same time, the sequence information of the encoded text is combined with the LSTM network. This method can better detect irony expressions, and can achieve good accuracy in the case of obvious or subtle irony expressions. Among them, the irony detection model based on the intra-sentence word pair relationship and contextual user characteristics is invented specifically. The invention provides discrimination basis for irony detection and is beneficial to distinguish irony texts without obvious contradictory word pairs. The accuracy of irony detection is improved from these two perspectives.

Description

technical field [0001] The invention relates to the field of emotion classification, in particular to an irony detection method based on the relationship between word pairs in a sentence and the characteristics of contextual users. Background technique [0002] Irony and sarcasm are rhetorical methods commonly used in social media. Irony is the use of words contrary to the original meaning to express the meaning, but with negative, ironic and mocking meanings. Sarcasm is the use of metaphors, exaggerations, etc. to expose, criticize, or ridicule people or things. Regarding the relationship between irony and sarcasm, it can be considered that sarcasm is a kind of irony that contains emotions (such as aggressive emotions). In this paper, irony and satire are collectively referred to as "irony", and no distinction is made between irony and satire. The figurative nature of irony poses a great challenge to the sentiment analysis task. [0003] At present, the research on iron...

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 Patents(China)
IPC IPC(8): G06F16/35G06K9/62
CPCG06F16/35G06F18/253
Inventor 姜明张雯张旻汤景凡戚铖杰腾海滨
Owner HANGZHOU DIANZI 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