Named entity recognition of railway dispatching command based on BiLSTM-CRF

Yandong Dong; Yekun Wang; Xinqin Li; Hongfei Cao

doi:10.1117/12.2689870

7 September 2023 Named entity recognition of railway dispatching command based on BiLSTM-CRF

Yandong Dong, Yekun Wang, Xinqin Li, Hongfei Cao

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 1279056 (2023) https://doi.org/10.1117/12.2689870
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

With the continuous development of China's railway, the workload of train dispatching command compilation is also increasing, so it is necessary to conduct in-depth research on the text data of dispatching command to improve the efficiency of dispatching command issuance. As an important task of text mining, named entity recognition is also a key step in analyzing text data of railway dispatching commands. In this paper, a named entity recognition model of scheduling command is constructed by combining bidirectional short-term memory neural network and conditional random field. The model identifies five entity types from the text of the dispatching order, namely, location, time, dispatching order type and train number, which can effectively improve the efficiency of dispatching order issuance. The experiment shows that the proposed scheduling command entity recognition model is significantly better than the previous methods in terms of accuracy, recall rate, F1 value, and so on, without the need to manually build features.

Citation Download Citation

Yandong Dong, Yekun Wang, Xinqin Li, and Hongfei Cao "Named entity recognition of railway dispatching command based on BiLSTM-CRF", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 1279056 (7 September 2023); https://doi.org/10.1117/12.2689870

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available