Search results
1 – 10 of over 4000Eun-Suk Yang, Jong Dae Kim, Chan-Young Park, Hye-Jeong Song and Yu-Seop Kim
In this paper, the problem of a nonlinear model – specifically the hidden unit conditional random fields (HUCRFs) model, which has binary stochastic hidden units between the data…
Abstract
Purpose
In this paper, the problem of a nonlinear model – specifically the hidden unit conditional random fields (HUCRFs) model, which has binary stochastic hidden units between the data and the labels – exhibiting unstable performance depending on the hyperparameter under consideration.
Design/methodology/approach
There are three main optimization search methods for hyperparameter tuning: manual search, grid search and random search. This study shows that HUCRFs’ unstable performance depends on the hyperparameter values used and its performance is based on tuning that draws on grid and random searches. All experiments conducted used the n-gram features – specifically, unigram, bigram, and trigram.
Findings
Naturally, selecting a list of hyperparameter values based on a researchers’ experience to find a set in which the best performance is exhibited is better than finding it from a probability distribution. Realistically, however, it is impossible to calculate using the parameters in all combinations. The present research indicates that the random search method has a better performance compared with the grid search method while requiring shorter computation time and a reduced cost.
Originality/value
In this paper, the issues affecting the performance of HUCRF, a nonlinear model with performance that varies depending on the hyperparameters, but performs better than CRF, has been examined.
Details
Keywords
Xinliang Liu, Liang Cheng, Guoning Chen, Xiaolei Wang and Jingqiu Wang
The purpose of this study is to provide a new convolutional neural network (CNN) model with multi-scale feature extractor to segment and recognize wear particles in complex…
Abstract
Purpose
The purpose of this study is to provide a new convolutional neural network (CNN) model with multi-scale feature extractor to segment and recognize wear particles in complex ferrograph images, especially fatigue and severe sliding wear particles, which are similar in morphology while different in wear mechanism.
Design/methodology/approach
A CNN model named DWear is proposed to semantically segment fatigue, severe sliding particles and four other types of particles, that is, chain, spherical, cutting and oxide particles, which unifies segmentation and recognition together. DWear is constructed using four modules, namely, encoder, densely connected atrous spatial pyramid pooling, decoder and fully connected conditional random field. Different from the architectures of ordinary semantic segmentation CNN models, a multi-scale feature extractor using cascade connections and a coprime atrous rate group is incorporated into the DWear model to obtain multi-scale receptive fields and better extract features of wear particles. Moreover, fully connected conditional random field module is adopted for post-processing to smooth coarse prediction and obtain finer results.
Findings
DWear is trained and verified on the ferrograph image data set, and experimental results show that the final Mean Pixel Accuracy is 95.6% and the Mean Intersection over Union is 92.2%, which means that the recognition and segmentation accuracy is higher than those of previous works.
Originality/value
DWear provides a promising approach for wear particle analysis and can be further developed in equipment condition monitoring applications.
Details
Keywords
Zhen Wang, Huanling Wang, Weiya Xu and W.C. Xie
This paper aims to analyze the influence of rotated anisotropy on the stability of slope, the random finite element method is used in this study.
Abstract
Purpose
This paper aims to analyze the influence of rotated anisotropy on the stability of slope, the random finite element method is used in this study.
Design/methodology/approach
The random field is generated by the discrete cosine transform (DCT) method, which can generate random field with different rotated angles conveniently.
Findings
Two idealized slopes are analyzed; it is observed that the rotated angle significantly affects the slope failure risk. The two examples support the conclusion that when the orientation of the layers is nearly perpendicular to the slip surface, the slope is in a relative stable condition. The results of heterogeneous slope with two clay layers demonstrate that the rotated angle of lower layer mainly controls the failure mechanism of the slope, and the rotated angle of upper layer exhibits a significant influence on the probability of slope failure.
Originality/value
The method for rotated anisotropy random field generation based on the DCT has a simple expression with few parameters and is convenient for implementation and practical application. The proposed method and the results obtained are useful for analyzing the stability of the heterogeneous slopes in engineering projects.
Details
Keywords
Na Xu, Yanxiang Liang, Chaoran Guo, Bo Meng, Xueqing Zhou, Yuting Hu and Bo Zhang
Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a…
Abstract
Purpose
Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.
Design/methodology/approach
Bidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.
Findings
Accordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.
Originality/value
This work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.
Details
Keywords
Maojian Chen, Xiong Luo, Hailun Shen, Ziyang Huang, Qiaojuan Peng and Yuqi Yuan
This study aims to introduce an innovative approach that uses a decoder with multiple layers to accurately identify Chinese nested entities across various nesting depths. To…
Abstract
Purpose
This study aims to introduce an innovative approach that uses a decoder with multiple layers to accurately identify Chinese nested entities across various nesting depths. To address potential human intervention, an advanced optimization algorithm is used to fine-tune the decoder based on the depth of nested entities present in the data set. With this approach, this study achieves remarkable performance in recognizing Chinese nested entities.
Design/methodology/approach
This study provides a framework for Chinese nested named entity recognition (NER) based on sequence labeling methods. Similar to existing approaches, the framework uses an advanced pre-training model as the backbone to extract semantic features from the text. Then a decoder comprising multiple conditional random field (CRF) algorithms is used to learn the associations between granularity labels. To minimize the need for manual intervention, the Jaya algorithm is used to optimize the number of CRF layers. Experimental results validate the effectiveness of the proposed approach, demonstrating its superior performance on both Chinese nested NER and flat NER tasks.
Findings
The experimental findings illustrate that the proposed methodology can achieve a remarkable 4.32% advancement in nested NER performance on the People’s Daily corpus compared to existing models.
Originality/value
This study explores a Chinese NER methodology based on the sequence labeling ideology for recognizing sophisticated Chinese nested entities with remarkable accuracy.
Details
Keywords
Bilal M’hamed Abidine, Belkacem Fergani, Mourad Oussalah and Lamya Fergani
The task of identifying activity classes from sensor information in smart home is very challenging because of the imbalanced nature of such data set where some activities occur…
Abstract
Purpose
The task of identifying activity classes from sensor information in smart home is very challenging because of the imbalanced nature of such data set where some activities occur more frequently than others. Typically probabilistic models such as Hidden Markov Model (HMM) and Conditional Random Fields (CRF) are known as commonly employed for such purpose. The paper aims to discuss these issues.
Design/methodology/approach
In this work, the authors propose a robust strategy combining the Synthetic Minority Over-sampling Technique (SMOTE) with Cost Sensitive Support Vector Machines (CS-SVM) with an adaptive tuning of cost parameter in order to handle imbalanced data problem.
Findings
The results have demonstrated the usefulness of the approach through comparison with state of art of approaches including HMM, CRF, the traditional C-Support vector machines (C-SVM) and the Cost-Sensitive-SVM (CS-SVM) for classifying the activities using binary and ubiquitous sensors.
Originality/value
Performance metrics in the experiment/simulation include Accuracy, Precision/Recall and F measure.
Details
Keywords
Si Shen, Chuan Jiang, Haotian Hu, Youshu Ji and Dongbo Wang
Reorganising unstructured academic abstracts according to a certain logical structure can help scholars not only extract valid information quickly but also facilitate the faceted…
Abstract
Purpose
Reorganising unstructured academic abstracts according to a certain logical structure can help scholars not only extract valid information quickly but also facilitate the faceted search of academic literature. This study aims to build a high-performance model for identifying of the functional structures of unstructured abstracts in the social sciences.
Design/methodology/approach
This study first investigated the structuring of abstracts in academic articles in the field of social sciences, using large-scale statistical analyses. Then, the functional structures of sentences in the abstract in a corpus of more than 3.5 million abstracts were identified from sentence classification and sequence tagging by using several models based on either machine learning or a deep learning approach, and the results were compared.
Findings
The results demonstrate that the functional structures of sentences in abstracts in social science manuscripts include the background, purpose, methods, results and conclusions. The experimental results show that the bidirectional encoder representation from transformers exhibited the best performance, the overall F1 score of which was 86.23%.
Originality/value
The data set of annotated social science abstract is generated and corresponding models are trained on the basis of the data set, both of which are available on Github (https://github.com/Academic-Abstract-Knowledge-Mining/SSCI_Abstract_Structures_Identification). Based on the optimised model, a Web application for the identification of the functional structures of abstracts and their faceted search in social sciences was constructed to enable rapid and convenient reading, organisation and fine-grained retrieval of academic abstracts.
Details
Keywords
Jinzhu Zhang, Yue Liu, Linqi Jiang and Jialu Shi
This paper aims to propose a method for better discovering topic evolution path and semantic relationship from the perspective of patent entity extraction and semantic…
Abstract
Purpose
This paper aims to propose a method for better discovering topic evolution path and semantic relationship from the perspective of patent entity extraction and semantic representation. On the one hand, this paper identifies entities that have the same semantics but different expressions for accurate topic evolution path discovery. On the other hand, this paper reveals semantic relationships of topic evolution for better understanding what leads to topic evolution.
Design/methodology/approach
Firstly, a Bi-LSTM-CRF (bidirectional long short-term memory with conditional random field) model is designed for patent entity extraction and a representation learning method is constructed for patent entity representation. Secondly, a method based on knowledge outflow and inflow is proposed for discovering topic evolution path, by identifying and computing semantic common entities among topics. Finally, multiple semantic relationships among patent entities are pre-designed according to a specific domain, and then the semantic relationship among topics is identified through the proportion of different types of semantic relationships belonging to each topic.
Findings
In the field of UAV (unmanned aerial vehicle), this method identifies semantic common entities which have the same semantics but different expressions. In addition, this method better discovers topic evolution paths by comparison with a traditional method. Finally, this method identifies different semantic relationships among topics, which gives a detailed description for understanding and interpretation of topic evolution. These results prove that the proposed method is effective and useful. Simultaneously, this method is a preliminary study and still needs to be further investigated on other datasets using multiple emerging deep learning methods.
Originality/value
This work provides a new perspective for topic evolution analysis by considering semantic representation of patent entities. The authors design a method for discovering topic evolution paths by considering knowledge flow computed by semantic common entities, which can be easily extended to other patent mining-related tasks. This work is the first attempt to reveal semantic relationships among topics for a precise and detailed description of topic evolution.
Details
Keywords
The tender documents, an essential data source for internet-based logistics tendering platforms, incorporate massive fine-grained data, ranging from information on tenderee…
Abstract
Purpose
The tender documents, an essential data source for internet-based logistics tendering platforms, incorporate massive fine-grained data, ranging from information on tenderee, shipping location and shipping items. Automated information extraction in this area is, however, under-researched, making the extraction process a time- and effort-consuming one. For Chinese logistics tender entities, in particular, existing named entity recognition (NER) solutions are mostly unsuitable as they involve domain-specific terminologies and possess different semantic features.
Design/methodology/approach
To tackle this problem, a novel lattice long short-term memory (LSTM) model, combining a variant contextual feature representation and a conditional random field (CRF) layer, is proposed in this paper for identifying valuable entities from logistic tender documents. Instead of traditional word embedding, the proposed model uses the pretrained Bidirectional Encoder Representations from Transformers (BERT) model as input to augment the contextual feature representation. Subsequently, with the Lattice-LSTM model, the information of characters and words is effectively utilized to avoid error segmentation.
Findings
The proposed model is then verified by the Chinese logistic tender named entity corpus. Moreover, the results suggest that the proposed model excels in the logistics tender corpus over other mainstream NER models. The proposed model underpins the automatic extraction of logistics tender information, enabling logistic companies to perceive the ever-changing market trends and make far-sighted logistic decisions.
Originality/value
(1) A practical model for logistic tender NER is proposed in the manuscript. By employing and fine-tuning BERT into the downstream task with a small amount of data, the experiment results show that the model has a better performance than other existing models. This is the first study, to the best of the authors' knowledge, to extract named entities from Chinese logistic tender documents. (2) A real logistic tender corpus for practical use is constructed and a program of the model for online-processing real logistic tender documents is developed in this work. The authors believe that the model will facilitate logistic companies in converting unstructured documents to structured data and further perceive the ever-changing market trends to make far-sighted logistic decisions.
Details
Keywords
Lichao Zhu, Hangzhou Yang and Zhijun Yan
The purpose of this paper is to develop a new method to extract medical temporal information from online health communities.
Abstract
Purpose
The purpose of this paper is to develop a new method to extract medical temporal information from online health communities.
Design/methodology/approach
The authors trained a conditional random-filed model for the extraction of temporal expressions. The temporal relation identification is considered as a classification task and several support vector machine classifiers are built in the proposed method. For the model training, the authors extracted some high-level semantic features including co-reference relationship of medical concepts and the semantic similarity among words.
Findings
For the extraction of TIMEX, the authors find that well-formatted expressions are easy to recognize, and the main challenge is the relative TIMEX such as “three days after onset”. It also shows the same difficulty for normalization of absolute date or well-formatted duration, whereas frequency is easier to be normalized. For the identification of DocTimeRel, the result is fairly well, and the relation is difficult to identify when it involves a relative TIMEX or a hypothetical concept.
Originality/value
The authors proposed a new method to extract temporal information from the online clinical data and evaluated the usefulness of different level of syntactic features in this task.
Details