Fine-grained word representation model-based sequence labeling model

A sequence labeling, fine-grained technology, applied in character and pattern recognition, special data processing applications, instruments, etc.

Active Publication Date: 2018-08-28
DALIAN UNIV OF TECH
View PDF4 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the Attention mechanism has made some progress in NER tasks, how to effectively integrate the dyn

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
  • Fine-grained word representation model-based sequence labeling model
  • Fine-grained word representation model-based sequence labeling model
  • Fine-grained word representation model-based sequence labeling model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The specific embodiments discussed are merely illustrative of implementations of the invention, and do not limit the scope of the invention. Embodiments of the present invention will be described in detail below in combination with technical solutions and accompanying drawings.

[0066] In order to represent the morphological information of words more accurately, the present invention designs a fine-grained word representation model Finger based on the Attention mechanism. At the same time, by combining Finger and BiLSTM-CRF model for sequence tagging tasks, ideal results have been achieved.

[0067] 1. Representation stage

[0068] In the representation stage, given an arbitrarily long sentence, the word vector representation and character vector representation of the corresponding word are respectively represented by formulas (1)-(6), and the word vector and character vector of the word sequence are connected by splicing.

[0069] 2. Coding stage

[0070] In the enc...

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 provides a fine-grained word representation model-based sequence labeling model, which is used for performing a sequence labeling task, and belongs to the field of computer application and natural language processing. The structure of the model is mainly composed of three parts including a feature representation layer, a BiLSTM layer and a CRF layer. When the sequence labeling task is performed by utilizing the model, firstly an attention mechanism-based character level word representation model Finger is proposed for fusing morphological information and character information ofwords; secondly the Finger and a BiLSTM-CRF model finish the sequence labeling task jointly; and finally a result with F1 of 91.09% is obtained in a CoNLL 2003 data set in end-to-end and no any feature engineering forms by a method. An experiment shows that the designed Finger model remarkably improves the recall rate of a sequence labeling system, so that the model identification capability is remarkably improved.

Description

technical field [0001] The invention belongs to the fields of computer application and natural language processing, and relates to a character-level model based on an attention mechanism and its application in sequence labeling tasks. The invention proposes a sequence labeling model based on a fine-grained word representation model. The main innovation is to design a fine-grained word representation model based on attention mechanism to describe the morphological information of words more accurately, globally and dynamically, and then propose a sequence tagging model based on the word representation model. The model not only has high sequence labeling ability, but also does not require feature engineering, and has strong interpretability. Background technique [0002] Sequence tagging tasks such as Part-of-Speech Tagging and Named Entity Recognition (NER) are the basic work in the field of natural language processing. Taking NER as an example, its main task is to identify ...

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): G06F17/27G06K9/62
CPCG06F40/30G06F18/2415
Inventor 张绍武林广和杨亮林鸿飞
Owner DALIAN UNIV OF TECH
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