Research on Document Classification in the Field of Construction

DOI

10.2991/iccia-19.2019.78How to use a DOI?

Keywords

Attention; Deep Learning; Document Classification; Construction.

Abstract

At present, the communication and preservation of project construction documents in most construction enterprises are still using traditional paper method, so the utilization of information is very low. This cannot guarantee the completeness, accuracy and systematic of architectural engineering records. At the same time, the environment for information management of construction documents is so complicated, which also increases the difficulty of document classification in the field of construction. This paper first constructs a corpus in the field of construction, then pre-treats and constructs word vector of documents to be categorized. Finally, finishing the task of classification with text classification model of Bi-LSTM combined with attention.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhenyang Ren
AU  - Fucheng Wan
AU  - Hongzhi Yu
AU  - Tiantian Wu
PY  - 2019/07
DA  - 2019/07
TI  - Research on Document Classification in the Field of Construction
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 501
EP  - 506
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.78
DO  - 10.2991/iccia-19.2019.78
ID  - Ren2019/07
ER  -