Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Processing Algorithm
Open Access
- 2 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 40216-40226
Abstract
Many electrical equipment malfunction text messages are collected during power system operation and maintenance procedures. These texts usually contain crucial information for maintenance and condition monitoring. Because these power system malfunction texts are characterized by multidomain vocabularies, complex-syntactic structures, and long sentences, it is challenging to for automated systems to capture their semantic meaning and essential information. To address this issue, we propose a hybrid natural language processing (hybrid-NLP) algorithm to extract entities that represent electrical equipment. This algorithm is composed of a dictionary-based method, a language technology platform (LTP) tool, and the bidirectional encoder representations from a transformers-conditional random field (BERT-CRF) model. Significantly, the softmax output layer of the bidirectional encoder representations from the transformers (BERT) model is replaced by the conditional random field (CRF) algorithm to strengthen the contextual relationships between words and thus solve the local optimization of the preferred word label. The effectiveness of the proposed hybrid-NLP method is verified on a realistic dataset. Moreover, a statistical analysis is conducted to provide a reference for the operation and maintenance of power systems.Keywords
Funding Information
- State Grid Corporation of China Headquarter Science and Technology Project (5600-201918181A-0-0-00)
This publication has 20 references indexed in Scilit:
- A Bootstrapping Approach With CRF and Deep Learning Models for Improving the Biomedical Named Entity Recognition in Multi-DomainsIEEE Access, 2019
- Power Fault Preplan Text Information Extraction Based on NLP2018
- Recent Named Entity Recognition and Classification techniques: A systematic reviewComputer Science Review, 2018
- Cross-Domain and Semisupervised Named Entity Recognition in Chinese Social Media: A Unified ModelIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- Building and Querying an Enterprise Knowledge GraphIEEE Transactions on Services Computing, 2017
- A new condition assessment method for distribution transformers based on operation data and record text mining technique2016
- Towards application of text mining for enhanced power network data analytics - part i: retrieval and ranking of textual data from the internet2016
- Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping2016
- The role of big data in improving power system operation and protection2013
- Information Resource Management: Foundation for Knowledge ManagementInformation Systems Management, 2001