Bidirectional Encoder Representations From Transformers Research Articles

LogCSS: Log anomaly detection based on BERT-CNN with context-semantics-statistics features

With the development of artificial intelligence, deep-learning-based log anomaly detection proves to be an important research topic. In this paper, we propose LogCSS, a novel log anomaly detection framework based on the Context-Semantics-Statistics Convolutional Neural Network (CSSCNN). It is the first model that uses BERT (Bidirectional Encoder Representation from Transformers) and CNN (Convolutional Neural Network) to extract the semantic, temporal, and correlational features of the logs. We combine the features with the statistic information of log templates for the classification model to improve the accuracy. We also propose a technique, DOOT (Deals with the Out-Of-Templates), for online template matching. The experimental research shows that our framework improves the average F1 score of the six best algorithms in the industry by more than 5% on the open-source dataset HDFS, and improves the average F1 score of the six best algorithms in the industry by more than 8% on the BGL dataset, LogCSS also performs better than other similar methods on our own constructed dataset.

Evaluating the validity of the nursing statements algorithmically generated based on the International Classifications of Nursing Practice for respiratory nursing care using large language models.

This study aims to facilitate the creation of quality standardized nursing statements in South Korea's hospitals using algorithmic generation based on the International Classifications of Nursing Practice (ICNP) and evaluation through Large Language Models. We algorithmically generated 15972 statements related to acute respiratory care using 117 concepts and concept composition models of ICNP. Human reviewers, Generative Pre-trained Transformers 4.0 (GPT-4.0), and Bio_Clinical Bidirectional Encoder Representations from Transformers (BERT) evaluated the generated statements for validity. The evaluation by GPT-4.0 and Bio_ClinicalBERT was conducted with and without contextual information and training. Of the generated statements, 2207 were deemed valid by expert reviewers. GPT-4.0 showed a zero-shot AUC of 0.857, which aggravated with contextual information. Bio_ClinicalBERT, after training, significantly improved, reaching an AUC of 0.998. Bio_ClinicalBERT effectively validates auto-generated nursing statements, offering a promising solution to enhance and streamline healthcare documentation processes.

Enriching Urdu NER with BERT Embedding, Data Augmentation, and Hybrid Encoder-CNN Architecture

Named Entity Recognition (NER) is an indispensable component of Natural Language Processing (NLP), which aims to identify and classify entities within text data. While Deep Learning (DL) models have excelled in NER for well-resourced languages such as English, Spanish, and Chinese, they face significant hurdles when dealing with low-resource languages such as Urdu. These challenges stem from the intricate linguistic characteristics of Urdu, including morphological diversity, a context-dependent lexicon, and the scarcity of training data. This study addresses these issues by focusing on Urdu Named Entity Recognition (U-NER) and introducing three key contributions. First, various pre-trained embedding methods are employed, encompassing Word2vec (W2V), GloVe, FastText, Bidirectional Encoder Representations from Transformers (BERT), and Embeddings from language models (ELMo). In particular, fine-tuning is performed on BERT BASE and ELMo using Urdu Wikipedia and news articles. Second, a novel generative Data Augmentation (DA) technique replaces Named Entities (NEs) with mask tokens, employing pre-trained masked language models to predict masked tokens, effectively expanding the training dataset. Finally, the study introduces a novel hybrid model combining a Transformer Encoder with a Convolutional Neural Network (CNN) to capture the intricate morphology of Urdu. These modules enable the model to handle polysemy, extract short- and long-range dependencies, and enhance learning capacity. Empirical experiments demonstrate that the proposed model, incorporating BERT embeddings and an innovative DA approach, attains the highest F1-score of 93.99%, highlighting its efficacy for the U-NER task.

Dynamic Bi-layer Graph Learning for Context-aware Sequential Recommendation

Sequential recommendations have received great attention in recent years due to their wide application in e-commerce, trip planning, and online education. Contexts reveal the intention of a user in a transaction such as consuming or purchasing an item, and highly affect her behaviour. However, existing techniques cannot fully capture the context-sensitive and dynamic sequential user behaviours for effective and efficient sequential recommendation. To address this limitation, we propose a novel Dynamic Bi-layer Graph learning (DBIG)-based framework for sequential recommendation, which learns the sequence dynamics of user behaviours and contexts. Specifically, we first propose a context graph to identify the relevant contexts to a target user. Then, we propose a transaction context graph that predicts the probability of a transaction happening under certain contexts. In addition, we apply BERT (Bidirectional Encoder Representations from Transformers) to our graph embedding for understanding the user sequential behaviours in bidirectional ways and generating recommendations. Finally, we propose a cluster-structure-based algorithm, which incrementally maintains the DBIG model and BERT over dynamic transaction updates. We evaluate our DBIG-based framework by conducting extensive experiments over five public datasets. The quantitative results demonstrate the superiority of our approach in terms of effectiveness and efficiency.

Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges

Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that they struggled to capture the contextual relationships across text inputs. The introduction of bidirectional encoder representations from transformers (BERT) leads to a robust encoder for the transformer model that can understand the broader context and deliver state-of-the-art performance across various NLP tasks. This has inspired researchers and practitioners to apply BERT to practical problems, such as information retrieval (IR). A survey that focuses on a comprehensive analysis of prevalent approaches that apply pretrained transformer encoders like BERT to IR can thus be useful for academia and the industry. In light of this, we revisit a variety of BERT-based methods in this survey, cover a wide range of techniques of IR, and group them into six high-level categories: (i) handling long documents, (ii) integrating semantic information, (iii) balancing effectiveness and efficiency, (iv) predicting the weights of terms, (v) query expansion, and (vi) document expansion. We also provide links to resources, including datasets and toolkits, for BERT-based IR systems. Additionally, we highlight the advantages of employing encoder-based BERT models in contrast to recent large language models like ChatGPT, which are decoder-based and demand extensive computational resources. Finally, we summarize the comprehensive outcomes of the survey and suggest directions for future research in the area.

CySecBERT : A Domain-Adapted Language Model for the Cybersecurity Domain

The field of cysec is evolving fast. Security professionals are in need of intelligence on past, current and —ideally — upcoming threats, because attacks are becoming more advanced and are increasingly targeting larger and more complex systems. Since the processing and analysis of such large amounts of information cannot be addressed manually, cysec experts rely on machine learning techniques. In the textual domain, pre-trained language models such as Bidirectional Encoder Representations from Transformers (BERT) have proven to be helpful as they provide a good baseline for further fine-tuning. However, due to the domain-knowledge and the many technical terms in cysec, general language models might miss the gist of textual information. For this reason, we create a high-quality dataset 1 and present a language model 2 specifically tailored to the cysec domain that can serve as a basic building block for cybersecurity systems. The model is compared on 15 tasks: Domain-dependent extrinsic tasks for measuring the performance on specific problems, intrinsic tasks for measuring the performance of the internal representations of the model, as well as general tasks from the SuperGLUE benchmark. The results of the intrinsic tasks show that our model improves the internal representation space of domain words compared with the other models. The extrinsic, domain-dependent tasks, consisting of sequence tagging and classification, show that the model performs best in cybersecurity scenarios. In addition, we pay special attention to the choice of hyperparameters against catastrophic forgetting, as pre-trained models tend to forget the original knowledge during further training.

Enhancing psychiatric rehabilitation outcomes through a multimodal multitask learning model based on BERT and TabNet: An approach for personalized treatment and improved decision-making

Evaluating the rehabilitation status of individuals with serious mental illnesses (SMI) necessitates a comprehensive analysis of multimodal data, including unstructured text records and structured diagnostic data. However, progress in the effective assessment of rehabilitation status remains limited. Our study develops a deep learning model integrating Bidirectional Encoder Representations from Transformers (BERT) and TabNet through a late fusion strategy to enhance rehabilitation prediction, including referral risk, dangerous behaviors, self-awareness, and medication adherence, in patients with SMI. BERT processes unstructured textual data, such as doctor's notes, whereas TabNet manages structured diagnostic information. The model's interpretability function serves to assist healthcare professionals in understanding the model's predictive decisions, improving patient care. Our model exhibited excellent predictive performance for all four tasks, with an accuracy exceeding 0.78 and an area under the curve of 0.70. In addition, a series of tests proved the model's robustness, fairness, and interpretability. This study combines multimodal and multitask learning strategies into a model and applies it to rehabilitation assessment tasks, offering a promising new tool that can be seamlessly integrated with the clinical workflow to support the provision of optimized patient care.

Deep Learning in Cybersecurity: A Hybrid BERT–LSTM Network for SQL Injection Attack Detection

In the past decade, cybersecurity has become increasingly significant, driven largely by the increase in cybersecurity threats. Among these threats, SQL injection attacks stand out as a particularly common method of cyber attack. Traditional methods for detecting these attacks mainly rely on manually defined features, making these detection outcomes highly dependent on the precision of feature extraction. Unfortunately, these approaches struggle to adapt to the increasingly sophisticated nature of these attack techniques, thereby necessitating the development of more robust detection strategies. This paper presents a novel deep learning framework that integrates Bidirectional Encoder Representations from Transformers (BERT) and Long Short-Term Memory (LSTM) networks, enhancing the detection of SQL injection attacks. Leveraging the advanced contextual encoding capabilities of BERT and the sequential data processing ability of LSTM networks, the proposed model dynamically extracts word and sentence-level features, subsequently generating embedding vectors that effectively identify malicious SQL query patterns. Experimental results indicate that our method achieves accuracy, precision, recall, and F1 scores of 0.973, 0.963, 0.962, and 0.958, respectively, while ensuring high computational efficiency.

Advancing Drug-Target Interaction prediction with BERT and subsequence embedding

Exploring the relationship between proteins and drugs plays a significant role in discovering new synthetic drugs. The Drug-Target Interaction (DTI) prediction is a fundamental task in the relationship between proteins and drugs. Unlike encoding proteins by amino acids, we use amino acid subsequence to encode proteins, which simulates the biological process of DTI better. For this research purpose, we proposed a novel deep learning framework based on Bidirectional Encoder Representation from Transformers (BERT), which integrates high-frequency subsequence embedding and transfer learning methods to complete the DTI prediction task. As the first key module, subsequence embedding allows to explore the functional interaction units from drug and protein sequences and then contribute to finding DTI modules. As the second key module, transfer learning promotes the model learn the common DTI features from protein and drug sequences in a large dataset. Overall, the BERT-based model can learn two kinds features through the multi-head self-attention mechanism: internal features of sequence and interaction features of both proteins and drugs, respectively. Compared with other methods, BERT-based methods enable more DTI-related features to be discovered by means of attention scores which associated with tokenized protein/drug subsequences.We conducted extensive experiments for the DTI prediction task on three different benchmark datasets. The experimental results show that the model achieves an average prediction metrics higher than most baseline methods. In order to verify the importance of transfer learning, we conducted an ablation study on datasets, and the results show the superiority of transfer learning. In addition, we test the scalability of the model on the dataset in unseen drugs and proteins, and the results of the experiments show that it is acceptable in scalability.

Adapting transformer-based language models for heart disease detection and risk factors extraction

Efficiently treating cardiac patients before the onset of a heart attack relies on the precise prediction of heart disease. Identifying and detecting the risk factors for heart disease such as diabetes mellitus, Coronary Artery Disease (CAD), hyperlipidemia, hypertension, smoking, familial CAD history, obesity, and medications is critical for developing effective preventative and management measures. Although Electronic Health Records (EHRs) have emerged as valuable resources for identifying these risk factors, their unstructured format poses challenges for cardiologists in retrieving relevant information. This research proposed employing transfer learning techniques to automatically extract heart disease risk factors from EHRs. Leveraging transfer learning, a deep learning technique has demonstrated a significant performance in various clinical natural language processing (NLP) applications, particularly in heart disease risk prediction. This study explored the application of transformer-based language models, specifically utilizing pre-trained architectures like BERT (Bidirectional Encoder Representations from Transformers), RoBERTa, BioClinicalBERT, XLNet, and BioBERT for heart disease detection and extraction of related risk factors from clinical notes, using the i2b2 dataset. These transformer models are pre-trained on an extensive corpus of medical literature and clinical records to gain a deep understanding of contextualized language representations. Adapted models are then fine-tuned using annotated datasets specific to heart disease, such as the i2b2 dataset, enabling them to learn patterns and relationships within the domain. These models have demonstrated superior performance in extracting semantic information from EHRs, automating high-performance heart disease risk factor identification, and performing downstream NLP tasks within the clinical domain. This study proposed fine-tuned five widely used transformer-based models, namely BERT, RoBERTa, BioClinicalBERT, XLNet, and BioBERT, using the 2014 i2b2 clinical NLP challenge dataset. The fine-tuned models surpass conventional approaches in predicting the presence of heart disease risk factors with impressive accuracy. The RoBERTa model has achieved the highest performance, with micro F1-scores of 94.27%, while the BERT, BioClinicalBERT, XLNet, and BioBERT models have provided competitive performances with micro F1-scores of 93.73%, 94.03%, 93.97%, and 93.99%, respectively. Finally, a simple ensemble of the five transformer-based models has been proposed, which outperformed the most existing methods in heart disease risk fan, achieving a micro F1-Score of 94.26%. This study demonstrated the efficacy of transfer learning using transformer-based models in enhancing risk prediction and facilitating early intervention for heart disease prevention.

Sustainable Scientific and Technological Talents Recommendation Method Based on Recommendation Algorithm

In today’s rapid development of global technology, the global demand for scientific and technological talents remains high. To provide a reliable talent referral channel, a talent recommendation model based on Bidirectional Encoder Representation from Transformers (BERT) and Bi-directional Long Short-Term Memory (BLSTM) was constructed. This model enables the matching of talented individuals with job opportunities. The results demonstrated that the accuracy and F1 value of BLSTM-BERT in the test set were 0.95 and 0.92, respectively. The precision rate, recall rate, F1-socre value and accuracy rate of BLSTM-CNN model were 0.96, 0.97, 0.96 and 0.97, respectively. The correct prediction rate of the talent recommendation model for the four types of talents was 1.0. It is evident that the talent recommendation model has a high accuracy in predicting talent categories and can precisely recommend necessary scientific and technological professionals for businesses.

Bridging the Gap

Effective organization and retrieval of news content are heavily reliant on accurate news classification. While the mountainous research has been conducted in resourceful languages like English and Chinese, the researches on under-resourced languages like the Kurdish language are severely lacking. To address this challenge, we introduce a hybrid approach called RFO-CNN in this paper. The proposed method combines an improved version of red fox optimization algorithm (RFO) and convolutional neural network (CNN) for finetuning CNN’s parameters. Our model’s efficacy was tested on two widely used Kurdish news datasets, KNDH and KDC-4007, both of which contain news articles classified into various categories. We compared the performance of RFO-CNN to other cutting-edge deep learning models such as bidirectional long short-term memory networks and bidirectional encoder representations from transformers (BERT) transformers, as well as classical machine learning approaches such as multinomial naive bayes, support vector machine, and K-nearest neighbors. We trained and tested our datasets using four different scenarios: 60:40, 70:30, 80:20, and 90:10. Our experimental results demonstrate the superiority of the RFO-CNN model across all scenarios, outperforming the benchmark BERT model and other machine learning models in terms of accuracy and F1-score.

Tibetan Sentence Boundaries Automatic Disambiguation Based on Bidirectional Encoder Representations from Transformers on Byte Pair Encoding Word Cutting Method

Sentence Boundary Disambiguation (SBD) is crucial for building datasets for tasks such as machine translation, syntactic analysis, and semantic analysis. Currently, most automatic sentence segmentation in Tibetan adopts the methods of rule-based and statistical learning, as well as the combination of the two, which have high requirements on the corpus and the linguistic foundation of the researchers and are more costly to annotate manually. In this study, we explore Tibetan SBD using deep learning technology. Initially, we analyze Tibetan characteristics and various subword techniques, selecting Byte Pair Encoding (BPE) and Sentencepiece (SP) for text segmentation and training the Bidirectional Encoder Representations from Transformers (BERT) pre-trained language model. Secondly, we studied the Tibetan SBD based on different BERT pre-trained language models, which mainly learns the ambiguity of the shad (“།”) in different positions in modern Tibetan texts and determines through the model whether the shad (“།”) in the texts has the function of segmenting sentences. Meanwhile, this study introduces four models, BERT-CNN, BERT-RNN, BERT-RCNN, and BERT-DPCNN, based on the BERT model for performance comparison. Finally, to verify the performance of the pre-trained language models on the SBD task, this study conducts SBD experiments on both the publicly available Tibetan pre-trained language model TiBERT and the multilingual pre-trained language model (Multi-BERT). The experimental results show that the F1 score of the BERT (BPE) model trained in this study reaches 95.32% on 465,669 Tibetan sentences, nearly five percentage points higher than BERT (SP) and Multi-BERT. The SBD method based on pre-trained language models in this study lays the foundation for establishing datasets for the later tasks of Tibetan pre-training, summary extraction, and machine translation.

Sentiment analysis with hotel customer reviews using FNet

Recent research has focused on opinion mining from public sentiments using natural language processing (NLP) and machine learning (ML) techniques. Transformer-based models, such as bidirectional encoder representations from transformers (BERT), excel in extracting semantic information but are resourceintensive. Google’s new research, mixing tokens with fourier transform, also known as FNet, replaced BERT’s attention mechanism with a non-parameterized fourier transform, aiming to reduce training time without compromising performance. This study fine-tuned the FNet model with a publicly available Kaggle hotel review dataset and investigated the performance of this dataset in both FNet and BERT architectures along with conventional machine learning models such as long short-term memory (LSTM) and support vector machine (SVM). Results revealed that FNet significantly reduces the training time by almost 20% and memory utilization by nearly 60% compared to BERT. The highest test accuracy observed in this experiment by FNet was 80.27% which is nearly 97.85% of BERT’s performance with identical parameters.

Predicting possible recommendations related to causes and consequences in the HAZOP study worksheet using natural language processing and machine learning: BERT, clustering, and classification

A set of recommendations is one of the most valuable outputs of the hazard and operability (HAZOP) study. The HAZOP study team provides recommendations when deficiencies are detected in the chemical process plant. These deficiencies can cause chemical process accidents and operability issues. This study employed a data-driven approach using natural language processing (NLP) and machine learning (ML) to predict potential recommendations based on causes and consequences. The dataset had no label; thus, clustering was used to label it. Firstly, bidirectional encoder representations from transformers (BERT) converted recommendation sentences into vectors. Secondly, uniform manifold approximation and projection (UMAP) and hierarchical density-based spatial clustering of applications with noise (HDBSCAN) were utilized to determine recommendation categories and label the dataset. Then, BERT was used to convert causes and consequences into vectors. Finally, a multi-layer perceptron (MLP) classifier was employed to predict possible recommendations based on causes and consequences. The class imbalance problem was handled by random over-sampling. The prediction accuracy of possible recommendations based on causes and consequences equals 93.7% and 89.5%, respectively. As a result of predicting potential recommendations utilizing causes and consequences, major recommendations will not be overlooked during the HAZOP study. This can further expand NLP and ML applications in HAZOP study automation.

Sentiment analysis and classification of Ghanaian football tweets from the 2022 FIFA World Cup

Football as an attractive sport generates huge volumes of tweets concerning fans' opinions, feelings, and judgments during prime events. Such data can be leveraged in sentiment analysis, an algorithmic approach to analyzing text in tweets by extracting emotional tones. This paper presents a novel benchmark dataset of 132,115 tweets collected during the 2022 world cup on 𝕏 (formerly Twitter) for football-related sentiment classification. We also performed sentiment analysis on the dataset using lexicon-based tools, traditional machine learning algorithms, and pre-trained models, robustly optimized bidirectional encoder representations from transformers (BERT)- pretraining approach RoBERTa and distilled version of BERT (DistilBERT) to understand the emotions and reactions of football fans during different phases of the football matches. Results from the study indicate that most tweets had neutral sentiments in both context-aware and context-free analysis. We also describe our novel GhaFootBERT, a sentiment classification model based on transfer learning on BERT, which provides an effective approach to sentiment classification of football-related tweets. Our model performs robustly, outperforming the traditional models with 92% accuracy.

Improving cyberbullying detection through multi-level machine learning

Cyberbullying is a known risk factor for mental health issues, demanding immediate attention. This study aims to detect cyberbullying on social media in alignment with the third sustainable development goal (SDG) for health and well-being. Many previous studies employ single-level classification, but this research introduces a multi-class multi-level (MCML) algorithm for a more detailed approach. The MCML approach incorporates two levels of classification: level one for cyberbullying or not cyberbullying, and level two for classifying cyberbullying by type. This study used a dataset of 47,000 tweets from Twitter with six class labels and employed an 80:20 training and testing data split. By integrating bidirectional encoder representations from transformers (BERT) and MCML at level two, we achieved a remarkable 99% accuracy, surpassing BERT-based single-level classification at 94%. In conclusion, the combination of MCML and BERT offers enhanced cyberbullying classification accuracy, contributing to the broader goal of promoting mental health and well-being.

Enhancing Arabic offensive language detection with BERT-BiGRU model

With the advent of Web 2.0, various platforms and tools have been developed to allow internet users to express their opinions and thoughts on diverse topics and occurrences. Nevertheless, certain users misuse these platforms by sharing hateful and offensive speeches, which has a negative impact on the mental health of internet society. Thus, the detection of offensive language has become an active area of research in the field of natural language processing. Rapidly detecting offensive language on the internet and preventing it from spreading is of great practical significance in reducing cyberbullying and self-harm behaviors. Despite the crucial importance of this task, limited work has been done in this field for nonEnglish languages such as Arabic. Therefore, in this paper, we aim to improve the results of Arabic offensive language detection without the need for laborious preprocessing or feature engineering work. To achieve this, we combine the bidirectional encoder representations from transformers (BERT) model model with a bidirectional gated recurrent unit (BiGRU) layer to further enhance the extracted context and semantic features. The experiments were conducted on the Arabic dataset provided by the SemEval 2020 Task 12. The evaluation results show the effectiveness of our model compared to the baseline and related work models by achieving a macro F1- score of 93.16%.

Unsupervised Anomaly Detection in Sequential Process Data

Abstract: In this study, we present three types of unsupervised anomaly detection to identify anomalous test-takers based on their action sequences in problem-solving tasks. The first method relies on the use of the Isolation Forest algorithm to detect anomalous test-takers based on raw action sequences extracted from process data. The second method transforms raw action sequences into contextual embeddings using the Bidirectional Encoder Representations from Transformers (BERT) model and then applies the Isolation Forest algorithm to detect anomalous test-takers. The third method follows the same procedure as the second method, but it includes an intermediary step of dimensionality reduction for the contextual embeddings before applying the Isolation Forest algorithm for detecting anomalous cases. To compare the outcomes of the three methods, we analyze the log files from test-takers in the US sample ( n = 2,021) who completed the problem-solving in technology-rich environments (PSTRE) section of the Programme for the International Assessment of Adult Competencies (PIAAC) 2012 assessment. The results indicated that different groups of test-takers were flagged as anomalous depending on the representation (raw action sequences vs. contextual embeddings) and dimensionality of action sequences. Also, when the contextual embeddings were used, a larger number of test-takers were flagged by the Isolation Forest algorithm, indicating the sensitivity of this algorithm to the dimensionality of input data.

Agile fusion: developing 'Eat at Right Place' sentiment analysis tool

This study presents the development and validation of the "Eat at Right Place Initiative," a sentiment analysis tool for restaurant reviews. Combining a user-centric approach with the Scrum framework, the mHealth agile development and evaluation framework was implemented, deviating from the initially considered Scrum framework. A multidisciplinary team navigated three phases, aligning sprints, goals, and backlogs. Phase 1 focused on product identification through interviews and surveys. Phase 2 involved development and alpha testing using a bidirectional encoder representation from transformers (BERT) rule-based sentiment analysis model. The final phase, beta testing, incorporated user feedback for usability enhancements. Ethical considerations were prioritized, ensuring participant consent and confidentiality. The study culminated in a robust aspect-based sentiment analysis model, effective in capturing nuanced insights from diverse restaurant aspects. Beta testing revealed actionable insights, marking the tool as fit for release. This sentiment analysis tool addresses consumer and owner needs, with iterative development and real-world testing laying the groundwork for future enhancements.