Enhanced conditional random field‐long short‐term memory for name entity recognition in English texts

Abstract

Named Entity recognition (NER) is the essential topic in the real world during the advanced development of technologies. Hence, in this paper, to develop Enhanced Conditional Random Field-Long Short-Term Memory (ECRF-LSTM) for NER in English language. The proposed ECRF-LSTM is combination of Conditional Random Field-Long Short-Term Memory (ECRF-LSTM) and Arithmetic Optimization Algorithm (AOA). This proposed method is utilizing to NER from the English texts. The proposed method is working with three phases such as preprocessing phase, feature extraction phase, and NER phase. Initially, the datasets are collected from the online system. In the pre-processing phase, removal of URL, removal of special symbol, username removal, tokenization and stop word removal are done. After that, the essential features such as domain weight, event weight, textual similarity, spatial similarity, temporal similarity, and Relative Document-Term Frequency Difference (RDTFD) are extracted and then applied for training the proposed model. To empower the training phase of CRF-LSTM method, AOA is utilized to select optimal weight parameter coefficients of CRF-LSTM for training the model parameters. The proposed method is validated by statistical measurements and compared with the conventional methods such as Convolutional Neural Network-Particle Swarm Optimization (CNN-PSO) and Convolutional Neural Network (CNN) respectively.