Implicit discourse relation recognition method based on multi-granularity generation image enhancement representation

A technology for image generation and relationship recognition, which is applied in the field of text relationship recognition and implicit text relationship recognition based on multi-granularity generated image enhancement representation, which can solve problems such as ambiguity and insufficient semantic understanding

Active Publication Date: 2020-08-04
TIANJIN UNIV
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although they capture the argument semantic information well to a certain extent, most of these methods only focus on the text itself, because text semantics may have problems

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
  • Implicit discourse relation recognition method based on multi-granularity generation image enhancement representation
  • Implicit discourse relation recognition method based on multi-granularity generation image enhancement representation
  • Implicit discourse relation recognition method based on multi-granularity generation image enhancement representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0040] The implementation method of the present invention is given by taking the Penn Discourse TreeBank (PDTB) data set as an example. For the overall framework of the method, see figure 1 shown. The algorithm flow of the whole system includes several steps such as data set preprocessing, text-image coding fusion, capturing important graphic information in arguments, modeling text-image interaction components, and text relationship prediction.

[0041] Specific steps are as follows:

[0042] (1) Dataset preprocessing

[0043] The Penn Discourse Treebank (PDTB) is a large-scale corpus annotated on 2,312 Wall Street Journal articles. According to different granularities, PDTB divi...

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 implicit discourse relation recognition method based on multi-granularity generated image enhancement representation, and provides a multi-granularity generated image and aneural network for enhancing argument vector representation by simulating an association strategy for the first time due to the problems of ambiguity, fuzziness and the like of texts. Corresponding images according to different granularities (sentence level and phrase level) of texts are introduced, which helps understand semantics of chapters. In order to better capture context information of a text image, text and image features are integrated according to the sequence information of the text .Important image-text information and interaction information are captured in an image-text vector sequence representation whole formed by splicing two arguments by utilizing a self-attention mechanism; therefore, argument vector representation is further enriched, feature vector representation usedfor recognizing the discourse relations is obtained, and finally the feature vector representation used for recognizing the discourse relations is input into the discourse relation recognition layerfor discourse relation recognition.

Description

technical field [0001] The invention relates to the technical field of discourse analysis in natural language processing, in particular to discourse relationship recognition technology, in particular to an implicit discourse relationship recognition method based on multi-granularity generated image enhancement representation. Background technique [0002] Discourse analysis is a fundamental task in natural language processing (NLP), which analyzes the underlying discourse relational structure and mines the connections between text units. At present, although great progress has been made on the task of explicit discourse relation recognition involving explicit connectives (such as "because", "but"), due to the absence of discourse connectives (Pitler et al., 2009) [2] , implicit discourse relation identification remains a challenge. Improving the implicit discourse relationship recognition task can help many popular Natural Language Processing (NLP) tasks, such as machine tr...

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): G06F40/30G06N3/04
CPCG06F40/30G06N3/044G06N3/045Y02D10/00
Inventor 贺瑞芳王建贺迎春郭凤羽朱永凯
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap