Supercharge Your Innovation With Domain-Expert AI Agents!

Implicit discourse relation identification method of interactive capsule network based on dynamic routing

A relational recognition and interactive technology, applied in instruments, electrical digital data processing, computing, etc.

Pending Publication Date: 2020-12-11
TIANJIN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Implicit discourse relationship identification remains challenging due to the lack of explicit connectives (Pitler et al., 2009) [1]

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 identification method of interactive capsule network based on dynamic routing
  • Implicit discourse relation identification method of interactive capsule network based on dynamic routing
  • Implicit discourse relation identification method of interactive capsule network based on dynamic routing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] 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.

[0058] The implementation method of the present invention is given by taking the Penn Discourse TreeBank (PDTB) data set as an example.

[0059] For the overall framework of the method, see figure 1 shown. The algorithm flow of the whole system includes the steps of data set preprocessing, obtaining the abstract representation of text arguments, generating argument feature capsules, feature aggregation, capturing argument interactions, and text relationship prediction.

[0060] Specific steps are as follows:

[0061] (1) Dataset preprocessing

[0062] The Penn Discourse Treebank (PDTB) is a large-scale corpus annotated on 2312 Wall Street Journal articles. According to different ...

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 identification method of an interactive capsule network based on dynamic routing. According to the method, argument interaction is fully capturedfrom the perspective of multiple discourse relations by utilizing dynamic interactive routing; and the argument features are aggregated into a potential discourse relationship representation in an iterative refinement manner to obtain discourse relationship implicit semantic clues of the argument features. Besides, all possible discourse relationships are considered, and a complex argument interaction mode is effectively captured, so that more accurate discourse relationship prediction is made.

Description

technical field [0001] The invention relates to the technical field of discourse analysis in natural language processing, in particular to the discourse relationship recognition technology, in particular to an implicit discourse relationship recognition method based on dynamic routing interactive capsule network. Background technique [0002] Discourse relations describe how two adjacent text units (such as discourse units, clauses or sentences), called Arg1 and Arg2, are logically related (such as causal relations, contrastive relations). Implicit discourse relationship identification remains challenging due to the lack of explicit connectives (Pitler et al., 2009) [1]. Identifying discourse relations can help many Natural Language Processing (NLP) tasks, such as machine translation (Meyer et al., 2015) [2], dialogue system (Ma et al., 2019) [3], etc. [0003] With the unprecedented success of deep learning in the field of NLP, neural network-based models have become the m...

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): G06F40/216G06F40/30
CPCG06F40/216G06F40/30
Inventor 韩玉桂贺瑞芳任冬伟贺迎春朱永凯黄静
Owner TIANJIN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com