Active learning based named entity recognition and its application in natural language coverless information hiding

Huiyu Sun, Ralph Grishman, Yingchao Wang

Research output: Contribution to journalArticle

Abstract

Named entity recognition systems trained on one domain usually have a substantial drop in performance when applied to a different domain. In this paper, we apply active learning to domain adaptation for named entity recognition systems, propose various sampling optimizations, and show that the labeling effort can be reduced by over 92% while achieving the same performance as supervised method. Named entity recognition can be effectively applied to information extraction, machine translation, text classification and many other areas. We propose a new application area for named entity recognition, namely in natural language information hiding: A novel coverless information hiding method based on text big data is proposed, utilizing named entities to mark the locations of the hidden information. Coverless information hiding is a brand new area of information hiding that achieves the transmission of hidden information without any modification in the carrier text. Furthermore, active learning allows our information hiding method to be applied to text from new domains without substantial labeling effort.

Original languageEnglish (US)
Pages (from-to)443-451
Number of pages9
JournalJournal of Internet Technology
Volume18
Issue number2
StatePublished - 2017

Fingerprint

Labeling
Sampling
Problem-Based Learning
Big data

Keywords

  • Active learning
  • Coverless information hiding
  • Named entity recognition
  • Natural language information hiding

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Cite this

Active learning based named entity recognition and its application in natural language coverless information hiding. / Sun, Huiyu; Grishman, Ralph; Wang, Yingchao.

In: Journal of Internet Technology, Vol. 18, No. 2, 2017, p. 443-451.

Research output: Contribution to journalArticle

@article{7d6e3b3cd0ce4963bab2df9cdfce6ff5,
title = "Active learning based named entity recognition and its application in natural language coverless information hiding",
abstract = "Named entity recognition systems trained on one domain usually have a substantial drop in performance when applied to a different domain. In this paper, we apply active learning to domain adaptation for named entity recognition systems, propose various sampling optimizations, and show that the labeling effort can be reduced by over 92{\%} while achieving the same performance as supervised method. Named entity recognition can be effectively applied to information extraction, machine translation, text classification and many other areas. We propose a new application area for named entity recognition, namely in natural language information hiding: A novel coverless information hiding method based on text big data is proposed, utilizing named entities to mark the locations of the hidden information. Coverless information hiding is a brand new area of information hiding that achieves the transmission of hidden information without any modification in the carrier text. Furthermore, active learning allows our information hiding method to be applied to text from new domains without substantial labeling effort.",
keywords = "Active learning, Coverless information hiding, Named entity recognition, Natural language information hiding",
author = "Huiyu Sun and Ralph Grishman and Yingchao Wang",
year = "2017",
language = "English (US)",
volume = "18",
pages = "443--451",
journal = "Journal of Internet Technology",
issn = "1607-9264",
publisher = "Taiwan Academic Network Management Committee",
number = "2",

}

TY - JOUR

T1 - Active learning based named entity recognition and its application in natural language coverless information hiding

AU - Sun, Huiyu

AU - Grishman, Ralph

AU - Wang, Yingchao

PY - 2017

Y1 - 2017

N2 - Named entity recognition systems trained on one domain usually have a substantial drop in performance when applied to a different domain. In this paper, we apply active learning to domain adaptation for named entity recognition systems, propose various sampling optimizations, and show that the labeling effort can be reduced by over 92% while achieving the same performance as supervised method. Named entity recognition can be effectively applied to information extraction, machine translation, text classification and many other areas. We propose a new application area for named entity recognition, namely in natural language information hiding: A novel coverless information hiding method based on text big data is proposed, utilizing named entities to mark the locations of the hidden information. Coverless information hiding is a brand new area of information hiding that achieves the transmission of hidden information without any modification in the carrier text. Furthermore, active learning allows our information hiding method to be applied to text from new domains without substantial labeling effort.

AB - Named entity recognition systems trained on one domain usually have a substantial drop in performance when applied to a different domain. In this paper, we apply active learning to domain adaptation for named entity recognition systems, propose various sampling optimizations, and show that the labeling effort can be reduced by over 92% while achieving the same performance as supervised method. Named entity recognition can be effectively applied to information extraction, machine translation, text classification and many other areas. We propose a new application area for named entity recognition, namely in natural language information hiding: A novel coverless information hiding method based on text big data is proposed, utilizing named entities to mark the locations of the hidden information. Coverless information hiding is a brand new area of information hiding that achieves the transmission of hidden information without any modification in the carrier text. Furthermore, active learning allows our information hiding method to be applied to text from new domains without substantial labeling effort.

KW - Active learning

KW - Coverless information hiding

KW - Named entity recognition

KW - Natural language information hiding

UR - http://www.scopus.com/inward/record.url?scp=85018835559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018835559&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85018835559

VL - 18

SP - 443

EP - 451

JO - Journal of Internet Technology

JF - Journal of Internet Technology

SN - 1607-9264

IS - 2

ER -