Ajou University repository

Word recovery in word-lost documents using an artificial intelligence methodology
Citations

SCOPUS

0

Citation Export

Publication Year
2018-01-01
Journal
2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018 - Proceedings of the 2018 International Conference on Artificial Intelligence, ICAI 2018
Publisher
CSREA Press
Citation
2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018 - Proceedings of the 2018 International Conference on Artificial Intelligence, ICAI 2018, pp.468-471
Keyword
Machine LearningSkim-Gram ModelWord Recovery
Mesh Keyword
Embedding techniqueGram modelsNetwork language
All Science Classification Codes (ASJC)
SoftwareArtificial Intelligence
Abstract
Documents are often physically damaged in part. Even if you save a damaged document online, it will be hard to recover it. Therefore, this study aims to develop an artificial intelligence methodology that can guess and recover lost words in documents. This study demonstrates that the Skip-Gram model can be used to construct relationships between words using the word embedding technique, a simplified form of the neural network language model. It also shows that the relationship between words can be used to infer words to fit in a specific part of a lost document.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36236
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85068402247&origin=inward
Type
Conference
Funding
This research was partially supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2016R1D1A1B03934129) and partially supported by the MSIP (Ministry of Science and ICT) under ICT R&D program (2017-0-01672) supervised by the IITP (Institute for Information & communications Technology Promotion).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Chung, Tae-Sun Image
Chung, Tae-Sun정태선
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.