Associated activation-driven enrichment

Understanding implicit information from a cognitive perspective

Jie Bai, Linjing Li, Dajun Zeng, Qiudan Li

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a novel text representation paradigm and a set of follow-up text representation models based on cognitive psychology theories. The intuition of our study is that the knowledge implied in a large collection of documents may improve the understanding of single documents. Based on cognitive psychology theories, we propose a general text enrichment framework, study the key factors to enable activation of implicit information, and develop new text representation methods to enrich text with the implicit information. Our study aims to mimic some aspects of human cognitive procedure in which given stimulant words serve to activate understanding implicit concepts. By incorporating human cognition into text representation, the proposed models advance existing studies by mining implicit information from given text and coordinating with most existing text representation approaches at the same time, which essentially bridges the gap between explicit and implicit information. Experiments on multiple tasks show that the implicit information activated by our proposed models matches human intuition and significantly improves the performance of the text mining tasks as well.

Original languageEnglish (US)
Article number8017419
Pages (from-to)2655-2668
Number of pages14
JournalIEEE Transactions on Knowledge and Data Engineering
Volume29
Issue number12
DOIs
StatePublished - Dec 1 2017
Externally publishedYes

Fingerprint

Chemical activation
Experiments

Keywords

  • Association rules
  • Cognitive simulation
  • Knowledge representation
  • Text analysis

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Associated activation-driven enrichment : Understanding implicit information from a cognitive perspective. / Bai, Jie; Li, Linjing; Zeng, Dajun; Li, Qiudan.

In: IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 12, 8017419, 01.12.2017, p. 2655-2668.

Research output: Contribution to journalArticle

@article{d2a2a9e69ba74904b3ac38aab3c84d85,
title = "Associated activation-driven enrichment: Understanding implicit information from a cognitive perspective",
abstract = "In this paper, we propose a novel text representation paradigm and a set of follow-up text representation models based on cognitive psychology theories. The intuition of our study is that the knowledge implied in a large collection of documents may improve the understanding of single documents. Based on cognitive psychology theories, we propose a general text enrichment framework, study the key factors to enable activation of implicit information, and develop new text representation methods to enrich text with the implicit information. Our study aims to mimic some aspects of human cognitive procedure in which given stimulant words serve to activate understanding implicit concepts. By incorporating human cognition into text representation, the proposed models advance existing studies by mining implicit information from given text and coordinating with most existing text representation approaches at the same time, which essentially bridges the gap between explicit and implicit information. Experiments on multiple tasks show that the implicit information activated by our proposed models matches human intuition and significantly improves the performance of the text mining tasks as well.",
keywords = "Association rules, Cognitive simulation, Knowledge representation, Text analysis",
author = "Jie Bai and Linjing Li and Dajun Zeng and Qiudan Li",
year = "2017",
month = "12",
day = "1",
doi = "10.1109/TKDE.2017.2745565",
language = "English (US)",
volume = "29",
pages = "2655--2668",
journal = "IEEE Transactions on Knowledge and Data Engineering",
issn = "1041-4347",
publisher = "IEEE Computer Society",
number = "12",

}

TY - JOUR

T1 - Associated activation-driven enrichment

T2 - Understanding implicit information from a cognitive perspective

AU - Bai, Jie

AU - Li, Linjing

AU - Zeng, Dajun

AU - Li, Qiudan

PY - 2017/12/1

Y1 - 2017/12/1

N2 - In this paper, we propose a novel text representation paradigm and a set of follow-up text representation models based on cognitive psychology theories. The intuition of our study is that the knowledge implied in a large collection of documents may improve the understanding of single documents. Based on cognitive psychology theories, we propose a general text enrichment framework, study the key factors to enable activation of implicit information, and develop new text representation methods to enrich text with the implicit information. Our study aims to mimic some aspects of human cognitive procedure in which given stimulant words serve to activate understanding implicit concepts. By incorporating human cognition into text representation, the proposed models advance existing studies by mining implicit information from given text and coordinating with most existing text representation approaches at the same time, which essentially bridges the gap between explicit and implicit information. Experiments on multiple tasks show that the implicit information activated by our proposed models matches human intuition and significantly improves the performance of the text mining tasks as well.

AB - In this paper, we propose a novel text representation paradigm and a set of follow-up text representation models based on cognitive psychology theories. The intuition of our study is that the knowledge implied in a large collection of documents may improve the understanding of single documents. Based on cognitive psychology theories, we propose a general text enrichment framework, study the key factors to enable activation of implicit information, and develop new text representation methods to enrich text with the implicit information. Our study aims to mimic some aspects of human cognitive procedure in which given stimulant words serve to activate understanding implicit concepts. By incorporating human cognition into text representation, the proposed models advance existing studies by mining implicit information from given text and coordinating with most existing text representation approaches at the same time, which essentially bridges the gap between explicit and implicit information. Experiments on multiple tasks show that the implicit information activated by our proposed models matches human intuition and significantly improves the performance of the text mining tasks as well.

KW - Association rules

KW - Cognitive simulation

KW - Knowledge representation

KW - Text analysis

UR - http://www.scopus.com/inward/record.url?scp=85028730858&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028730858&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2017.2745565

DO - 10.1109/TKDE.2017.2745565

M3 - Article

VL - 29

SP - 2655

EP - 2668

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

SN - 1041-4347

IS - 12

M1 - 8017419

ER -