Search

Power safety named entity recognition (NER) is essential for determining the cause of faults, assessing potential risks, and planning maintenance schedules, contributing to the comprehension and analysis of power safety documentation content and structure. Such analysis is crucial for the development of a knowledge graph within the power safety domain and the augmentation of the associated dataset. This paper introduces a power safety NER model using efficiently learning an encoder that classifies token replacements accurately (ELECTRA) model. This model employs root mean square layer normalization (RMSNorm) and the switched gated linear unit (SwiGLU) activation function, which substitutes the conventional layer normalization (LayerNorm) and the Gaussian error linear units (GeLU). This model also integrates bidirectional long short-term memory (BiLSTM) with conditional random fields (CRF) to bolster performance in NER tasks. Experimental results show that the improved ELECTRA model achieved an F1 value of 93% on the constructed power safety NER dataset. It outperforms the BERT-BiLSTM-CRF model, achieving a 3.3% performance improvement. [ABSTRACT FROM AUTHOR]

As an extension of the transformer architecture, the BERT model has introduced a new paradigm for natural language processing, achieving impressive results in various downstream tasks. However, high-performance BERT-based models—such as ELECTRA, ALBERT, and RoBERTa—suffer from limitations such as poor continuous learning capability and insufficient understanding of domain-specific documents. To address these issues, we propose the use of an attention mechanism to combine BERT-based models with neural topic models. Unlike traditional stochastic topic modeling, neural topic modeling employs artificial neural networks to learn topic representations. Furthermore, neural topic models can be integrated with other neural models and trained to identify latent variables in documents, thereby enabling BERT-based models to sufficiently comprehend the contexts of specific fields. We conducted experiments on three datasets—Movie Review Dataset (MRD), 20Newsgroups, and YELP—to evaluate our model's performance. Compared to the vanilla model, the proposed model achieved an accuracy improvement of 1–2% for the ALBERT model in multiclassification tasks across all three datasets, while the ELECTRA model showed an accuracy improvement of less than 1%. [ABSTRACT FROM AUTHOR]

The task of automatically evaluating acceptability judgments has relished increasing success in Natural Language Processing, starting from including the Corpus of Linguistic Acceptability (CoLa) in the GLUE benchmark dataset. CoLa spawned a thread that led to the development of several similar datasets in different languages, broadening the investigation possibilities to many languages other than English. In this study, leveraging the Italian Corpus of Linguistic Acceptability (ItaCoLA), comprising nearly 10,000 sentences with acceptability judgments, we propose a new methodology that utilizes the neural language model ELECTRA. This approach exceeds the scores obtained from current baselines and demonstrates that it can overcome language-specific limitations in dealing with specific phenomena. [ABSTRACT FROM AUTHOR]

Steel is one of the most manufactured materials in modern society, with 1.9 billion metric tons produced annually for use in building materials, vehicles, wind-turbines, and appliances, among many other applications. As you might expect for something so ubiquitous, the technology used to manufacture steel is also quite mature, having been first identified over 4,000 years ago and heavily industrialized in the 19th century. The general approach is to mine iron ore from the earth's crust and refine that ore to metallic iron (i.e., ironmaking) which is then combined with carbon and other elements to make steel products (i.e., steelmaking). However, conventional steel manufacturing relies primarily on carbon-based fuels, such as coal, to create the high temperatures (≈ 1600°C) required for the process and can emit as much as 2.2 tons of CO2 per ton of crude steel produced.1 The iron ore reduction step accounts for 90% of CO2 emissions associated with steel production. The heightened effort to decarbonize industrial process and reverse climate change is putting pressure on this 600+ year-old technology to shift to lowcarbon alternatives, especially considering that the steel industry is responsible for ≈ 7% of all global CO2 emissions annually. [ABSTRACT FROM AUTHOR]

In natural language processing (NLP), a Question Answering System (QAS) refers to a system or model that is designed to understand and respond to user queries in natural language. As we navigate through the recent advancements in QAS, it can be observed that there is a paradigm shift of the methods used from traditional machine learning and deep learning approaches towards transformer-based language models. While significant progress has been made, the utilization of these models for historical QAS and the development of QAS for Malay language remain largely unexplored. This research aims to bridge the gaps, focusing on developing a Multilingual QAS for history of Malaysia by utilizing a transformer-based language model. The system development process encompasses various stages, including data collection, knowledge representation, data loading and pre-processing, document indexing and storing, and the establishment of a querying pipeline with the retriever and reader. A dataset with a collection of 100 articles, including web blogs related to the history of Malaysia, has been constructed, serving as the knowledge base for the proposed QAS. A significant aspect of this research is the use of the translated dataset in English instead of the raw dataset in Malay. This decision was made to leverage the effectiveness of well-established retriever and reader models that were trained on English data. Moreover, an evaluation dataset comprising 100 question-answer pairs has been created to evaluate the performance of the models. A comparative analysis of six different transformer-based language models, namely DeBERTaV3, BERT, ALBERT, ELECTRA, MiniLM, and RoBERTa, has been conducted, where the effectiveness of the models was examined through a series of experiments to determine the best reader model for the proposed QAS. The experimental results reveal that the proposed QAS achieved the best performance when employing RoBERTa as the reader model. Finally, the proposed QAS was deployed on Discord and equipped with multilingual support through the incorporation of language detection and translation modules, enabling it to handle queries in both Malay and English. Doi: 10.28991/ESJ-2024-08-02-019 Full Text: PDF

Power safety named entity recognition (NER) is essential for determining the cause of faults, assessing potential risks, and planning maintenance schedules, contributing to the comprehension and analysis of power safety documentation content and structure. Such analysis is crucial for the development of a knowledge graph within the power safety domain and the augmentation of the associated dataset. This paper introduces a power safety NER model using efficiently learning an encoder that classifies token replacements accurately (ELECTRA) model. This model employs root mean square layer normalization (RMSNorm) and the switched gated linear unit (SwiGLU) activation function, which substitutes the conventional layer normalization (LayerNorm) and the Gaussian error linear units (GeLU). This model also integrates bidirectional long short-term memory (BiLSTM) with conditional random fields (CRF) to bolster performance in NER tasks. Experimental results show that the improved ELECTRA model achieved an F1 value of 93% on the constructed power safety NER dataset. It outperforms the BERT-BiLSTM-CRF model, achieving a 3.3% performance improvement.

As an extension of the transformer architecture, the BERT model has introduced a new paradigm for natural language processing, achieving impressive results in various downstream tasks. However, high-performance BERT-based models—such as ELECTRA, ALBERT, and RoBERTa—suffer from limitations such as poor continuous learning capability and insufficient understanding of domain-specific documents. To address these issues, we propose the use of an attention mechanism to combine BERT-based models with neural topic models. Unlike traditional stochastic topic modeling, neural topic modeling employs artificial neural networks to learn topic representations. Furthermore, neural topic models can be integrated with other neural models and trained to identify latent variables in documents, thereby enabling BERT-based models to sufficiently comprehend the contexts of specific fields. We conducted experiments on three datasets—Movie Review Dataset (MRD), 20Newsgroups, and YELP—to evaluate our model’s performance. Compared to the vanilla model, the proposed model achieved an accuracy improvement of 1–2% for the ALBERT model in multiclassification tasks across all three datasets, while the ELECTRA model showed an accuracy improvement of less than 1%.

Os estudos tradicionais dedicados à tragédia Electra, de Sófocles, enfatizaram uma dicotomia entre os longos discursos lúgubres de Electra, sobretudo na primeira metade da peça, e a eficiência das ações executadas por Orestes para levar a cabo o desenlace da trama. Buscando apoio em comentadores contemporâneos dessa obra, que têm destacado a dimensão performativa de certos atos de fala aí existentes, pretendo revisitar essa discussão a fim de suscitar uma nova possibilidade de consideração sobre o papel desempenhado por Electra na peça. A interpretação aqui aventada pretende dar conta de certas estranhezas do texto trágico, sugerindo uma melhor compreensão de detalhes da cena em que Clitemnestra é assassinada, bem como da conclusão aparentemente amoral avançada pela forma como a peça se encerra, sem que o matricídio pareça ter quaisquer consequências nefastas (como é o caso nas versões que Ésquilo e Eurípides propõem desse mesmo incidente mítico).

Social media contains useful information about people and society that could help advance research in many different areas of health (e.g. by applying opinion mining, emotion/sentiment analysis and statistical analysis) such as mental health, health surveillance, socio-economic inequality and gender vulnerability. User demographics provide rich information that could help study the subject further. However, user demographics such as gender are considered private and are not freely available. In this study, we propose a model based on transformers to predict the user's gender from their images and tweets. The image-based classification model is trained in two different methods: using the profile image of the user and using various image contents posted by the user on Twitter. For the first method a Twitter gender recognition dataset, publicly available on Kaggle and for the second method the PAN-18 dataset is used. Several transformer models, i.e. vision transformers (ViT), LeViT and Swin Transformer are fine-tuned for both of the image datasets and then compared. Next, different transformer models, namely, bidirectional encoders representations from transformers (BERT), RoBERTa and ELECTRA are fine-tuned to recognize the user's gender by their tweets. This is highly beneficial, because not all users provide an image that indicates their gender. The gender of such users could be detected from their tweets. The significance of the image and text classification models were evaluated using the Mann-Whitney U test. Finally, the combination model improved the accuracy of image and text classification models by 11.73 and 5.26% for the Kaggle dataset and by 8.55 and 9.8% for the PAN-18 dataset, respectively. This shows that the image and text classification models are capable of complementing each other by providing additional information to one another. Our overall multimodal method has an accuracy of 88.11% for the Kaggle and 89.24% for the PAN-18 dataset and outperforms state-of-the-art models. Our work benefits research that critically require user demographic information such as gender to further analyze and study social media content for health-related issues.

The Surface Water & Ocean Topography (SWOT) mission is a joint NASA/CNES mission launched on December 16th, 2022 dedicated to oceanography and continental hydrology. Once the scientific mission is over, SWOT will have to perform a controlled re-entry to comply with the French Space Operation Act (FSOA). Indeed, the launch authorization is subject to the respect of the FSOA, fully applicable since 2020. The main requirement applying to the end-of-life of the satellite consists in limiting the casualty area and then the probability of having a victim on ground under the threshold of 10−4 in case of a natural re-entry. With a mass over two tons and a casualty area of about 47 m2, SWOT cannot comply with this requirement. Thus, the platform has been designed with a specific propulsion system to carry out end-of-life maneuvers leading to an atmospheric re-entry and impact in the South Pacific Ocean Uninhabited Area (SPOUA). CNES is in charge of defining the re-entry maneuvers strategy, performing end-of-life operations and evaluating the risk of casualties in case of failure during nominal strategy. This paper addresses these topics. The computation of the ten maneuvers used to decrease the perigee altitude and finally target the SPOUA is performed using the DOORS tool. Before describing the maneuvers strategy, this paper presents an overview of the current functionalities of this tool, which has been already used during the five ATV missions and ASTRA-1K de-orbit twenty years ago. DOORS is mainly used for mission analysis purposes, but for end-of-life operations it can be activated by the operational Flight Dynamics System (FDS). Finally, the casualty risk estimation relies on the use of two other CNES tools, DEBRISK and ELECTRA, whose methods are presented. The list of surviving fragments has been computed using the new DEBRISK-V3 methodology in case of controlled and uncontrolled re-entry. The risk of human casualty is evaluated using ELECTRA and its Monte Carlo simulations. This tool generates numerous trajectories of the satellite and its fragments with various dispersed variables. The impact locations compared to an up-to-date grid of the World population lead to the probability of victims. The complete risk of SWOT controlled re-entry encompasses both the risk related to a failure during the last re-entry maneuver and the risk associated with the natural re-entry in case a failure occurs before this last burn (during the mission or during the first re-entry maneuvers). Both of them are weighted by their probability of occurrence. • SWOT controlled re-entry strategy to fulfill French regulation. • Robustness test of the nominal strategy made of 10 maneuvers. • Latest aerothermodynamic models used to build the list of surviving fragments. • Probability of victims considers contingencies during the whole re-entry operation. • Combination of several CNES softwares: DOORS, PSIMU, DEBRISK, ELECTRA. [ABSTRACT FROM AUTHOR]

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it is becoming crucial to identify ion-binding sites. The accurate identification of protein–ion binding sites helps us to understand proteins' biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion-binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46%, respectively, in the F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools, producing prediction results for a hundred sequences for a specific ion in under ten minutes. [ABSTRACT FROM AUTHOR]

Visual question answering (VQA) is a task that generates or predicts an answer to a question in human language about visual images. VQA is an active field combining two AI branches: NLP and computer vision. VQA in the medical field is still at an early stage, and it needs vast efforts and exploration to reach practical usage. This paper proposes two models that are utilized in the latest vision and NLP transformers that outperform the SOTA and have not yet been utilized in medical VQA. The ELECTRA-base transformer is used for textual feature extraction, whereas SWIN is used for visual feature extraction. In the SOTA medical VQA, selecting the model is based on the model that achieves the highest validation accuracy or the last model in training. The first proposed model, the best-value-based model, is selected based on the highest validation accuracy. The second model, the greedy-soup-based model, uses a greedy soup technique based on the fusion of multiple fine-tuned models to set the model parameters. The greedy soup selects the model parameters by fusing the model parameters that have significant performance on the validation accuracy in training. The greedy-soup-based model outperforms the best-value-based model, and both proposed models outperform the SOTA, which has an accuracy of 83.49%. The greedy-soup-based model is optimized with batch size and learning rate. During the optimization, seven extra models exceed the SOTA accuracy. The best model trained with a learning rate of 1.0 × 10 − 4 and batch size 16 achieves an accuracy of 87.41%. [ABSTRACT FROM AUTHOR]

The Electra myth has been a popular subject throughout the centuries for dramatists. The three great ancient Greek tragedians (Aeschylus, Sophocles, and Euripides) each created his own version of the myth, and these plays have been and continue to be translated or adapted into various languages. In contradiction to the famous phrase “lost in translation,” adaptations may incorporate political or cultural aspects of the country in which they are conceived, giving them even greater substance and meaning. The purpose of this paper, in turn, is two-fold. I begin by presenting and exploring the differences among the three Greek versions of the ancient tragedians and their implications. However, the majority of this paper focuses around three twentieth-century adaptations of each of the playwrights’ versions (namely, Jean Giraudoux’s French Électre, Hugo von Hofmannsthal’s German Elektra, and Eugene O’Neill’s American Mourning Becomes Electra). In addition to analyzing the changes made by these adaptations from their Greek “originals,” I also address why each adaptation may have chosen a particular Greek text as its source, as well as the political or social influences behind each adaptation.

Traditional studies dedicated to Sophocles’ tragedy Electra have emphasized a dichotomy between Electra’s long dismal speeches, especially in the first half of the play, and the efficiency of Orestes’ actions to carry out the outcome of the plot. Seeking support from contemporary commentators on this work, who have emphasized the performative dimension of certain speech acts there, I intend to revisit this discussion in order to elicit a new possibility of considering Electra’s role in the play. The interpretation suggested here accounts for certain strangeness of this tragic text and advances a better understanding of some details of the scene in which Clytemnestra is murdered, as well as the seemingly amoral conclusion advanced by the way the work ends, without the matricide seeming to have any harmful consequences (as it happens in the versions that Aeschylus and Euripides propose of this same mythic event). [ABSTRACT FROM AUTHOR]

Adverse event (AE) management is crucial to improve anti-cancer treatment outcomes, hut it is reported that some AE signals can he missed in clinical visits. Thus, monitoring AE signals seamlessly, including events outside hospitals, would he helpful for early intervention. Here we investigated how to detect AE signals from texts written hy cancer patients themselves hy developing deep-learning (DL) models to classify posts mentioning AEs according to severity grade, in order to focus on those that might need immediate treatment interventions. Using patient hlogs written in Japanese hy cancer patients as a data source, we huilt DL models hased on three approaches, BERT, ELECTRA, and T5. Among these models, T5 showed the hest F1 scores for hoth Grade ≥ 1 and ≥ 2 article classification tasks (0.85 and 0.53, respectively). This model might henefit patients hy enahling earlier AE signal detection, therehy improving quality of life. [ABSTRACT FROM AUTHOR]

Keyword extraction is an effective way to quickly identify key elements in text. It can accelerate the identification of key factors that play a role in accidents when applied to incident report analysis. Our research presents an innovative process for extracting keywords from incident reports with the pre-trained natural language processing models. We utilized fine-tuning techniques to integrate a BiLSTM-CRF with a fully-connected layer and pre-trained natural language models. The process of extracting keyphrases is approached as a task of labeling sequences. To analyze incident reports from Korea, we employ pre-trained models customized for the Korean context, such as KoBERT and KoELECTRA. Our approach is assessed using a range of metrics, including accuracy, area under the curve (AUC), F1-score, slot error rate (SER), and simple matching coefficient (SMC). In contrast to traditional approaches which mainly concentrate on document summarization, our research provides a distinct method tailored to identifying falling objects as the main cause of accidents. Our findings demonstrate that the ELECTRA-based model with a BiLSTM-CRF outperforms other models, achieving an accuracy of 0.943, an AUC of 0.991, and a low SER of 0.075. The F1-score and SMC closely resemble the BERT-based model with a BiLSTM-CRF, with no significant differences observed within the 95% confidence interval. These results underscore the potential of fine-tuning pre-trained models for post-hoc traffic accident analysis. This method offers a swift preliminary step to identify the key factors before human analysis, presenting a multifaceted strategy to enhance road safety and prevent accidents.

Este trabajo pretende analizar la fraseología empleada por Benito Pérez Galdós en una de sus obras de teatro más conocidas, Electra. Se procederá a una recopilación y análisis de las locuciones, que representan una muestra de la naturalidad y expresividad del lenguaje empleado por el escritor. Luego pasaremos a comprobar el uso actual de estas unidades fraseológicas, para destacar la actualidad de la lengua del autor. Se hará una investigación en los corpus del español actual de la Real Academia Española, para destacar el uso actual de estos fraseologismos, frente a otros ya desaparecidos del uso cotidiano.

Numerical reasoning in machine reading comprehension (MRC) has demonstrated significant performance improvements in the past few years. However, due to the process being restricted to specific languages, low-resource languages are not considered, and MRC studies on such languages are limited. In addition, the methods that rely on existing information extracted within the span of a paragraph have limitations in responding to questions requiring actual reasoning. To overcome these shortcomings, this study establishes a dataset for learning Korean Question and Answering (QA) models that not only answer within the span of passages but also perform numerical reasoning on passages and questions. Its efficacy was verified by training the model. We recruited eight annotators to tag the ground truth label, and they annotated datasets with 920, 115, and 115 passages in the train, dev, and test, respectively. A simple yet sophisticated automatic inter-annotation tool was created by effectively reducing the possibility of inaccuracy and error entailed by humans in the data construction process. This tool used common KoBERT and KoELECTRA. We defined four general conditions, and six conditions humans must inspect and fine-tune the pre-trained language models with numerically aware architecture. The KoELECTRA and NumNet+ with KoELECTRA were fine-tuned, and experiments in identical hyperparameter settings showed that compared with other models, the performance of NumNet+ with KoELECTRA was higher by more than 1.3 points. Our research contributes to the Korean MRC research and suggests potential and insight into MRC models capable of numerical reasoning.

This research aimed to evaluate the performance of the A Lite BERT (ALBERT), efficiently learning an encoder that classifies token replacements accurately (ELECTRA) and a robust optimized BERT pretraining approach (RoBERTa) models to support the development of the Indonesian language question and answer system model. The evaluation carried out used Indonesian, Malay and Esperanto. Here, Esperanto was used as a comparison of Indonesian because it is international, which does not belong to any person or country and this then make it neutral. Compared to other foreign languages, the structure and construction of Esperanto is relatively simple. The dataset used was the result of crawling Wikipedia for Indonesian and Open Super-large Crawled ALMAnaCH coRpus (OSCAR) for Esperanto. The size of the token dictionary used in the test used approximately 30,000 sub tokens in both the SentencePiece and byte-level byte pair encoding methods (ByteLevelBPE). The test was carried out with the learning rates of 1e-5 and 5e-5 for both languages in accordance with the reference from the bidirectional encoder representations from transformers (BERT) paper. As shown in the final result of this study, the ALBERT and RoBERTa models in Esperanto showed the results of the loss calculation that were not much different. This showed that the RoBERTa model was better to implement an Indonesian question and answer system. [ABSTRACT FROM AUTHOR]

Abstract Motivation Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available. Results We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it is becoming crucial to identify ion-binding sites. The accurate identification of protein–ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion-binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46%, respectively, in the F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools, producing prediction results for a hundred sequences for a specific ion in under ten minutes.

In last years, coreference resolution has received a sensibly performance boost exploiting different pre-trained Neural Language Models, from BERT to SpanBERT until Longformer. This work is aimed at assessing, for the first time, the impact of ELECTRA model on this task, moved by the experimental evidence of an improved contextual representation and better performance on different downstream tasks. In particular, ELECTRA has been employed as representation layer in an assessed neural coreference architecture able to determine entity mentions among spans of text and to best cluster them. The architecture itself has been optimized: i) by simplifying the modality of representation of spans of text but still considering both the context they appear and their entire content, ii) by maximizing both the number and length of input textual segments to exploit better the improved contextual representation power of ELECTRA, iii) by maximizing the number of spans of text to be processed, since potentially representing mentions, preserving computational efficiency. Experimental results on the OntoNotes dataset have shown the effectiveness of this solution from both a quantitative and qualitative perspective, and also with respect to other state-of-the-art models, thanks to a more proficient token and span representation. The results also hint at the possible use of this solution also for low-resource languages, simply requiring a pre-trained version of ELECTRA instead of language-specific models trained to handle either spans of text or long documents.

In this article, a criticality and depletion analysis of the European Lead-Cooled Training Reactor (ELECTRA), a low-power, compact, fast lead-cooled reactor, was performed. The active core model and simulations were made by using the MCNPX code. First, the model is compared with the reference and the influence of the reflector radius on the system is analyzed. Secondly, it was simulated the fuel combustion after 30 years of continuous operation of the ELECTRA, managing to evaluate the transmutation of a reprocessed fuel in a compact lead-cooled reactor.

Motivation: Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available. Results: We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks. [ABSTRACT FROM AUTHOR]

In recent years, the impact of Neural Language Models has changed every field of Natural Language Processing. In this scenario, coreference resolution has been among the least considered task, especially in language other than English. This work proposes a coreference resolution system for Italian, based on a neural end-to-end architecture integrating ELECTRA language model and trained on OntoCorefIT, a novel Italian dataset built starting from OntoNotes. Even if some approaches for Italian have been proposed in the last decade, to the best of our knowledge, this is the first neural coreference resolver aimed specifically to Italian. The performance of the system is evaluated with respect to three different metrics and also assessed by replacing ELECTRA with the widely-used BERT language model, since its usage has proven to be effective in the coreference resolution task in English. A qualitative analysis has also been conducted, showing how different grammatical categories affect performance in an inflectional and morphological-rich language like Italian. The overall results have shown the effectiveness of the proposed solution, providing a baseline for future developments of this line of research in Italian.

Electra was developed by an unknown man, Electra01. Following its emergence in cryptocurrency markets in 2018, its market capitalization briefly reached 136 billion USD, exceeding Bitcoin in value. The project’s community of 20,000 individuals, wrote its white papers, updated its blockchain, instituted a foundation, introduced a payment system, and voted to be the best crypto project in 2020 in the world by a global vote. Following a fundamental controversy in its community, Electra collapsed as the founder sold his hundreds of millions of Electras in November 2020, effectively killing the project. Within a short period, the community left the founder behind, and moved on to a new project, giving (re)birth to their community money, this time called Electra Protocol. Drawing on an empirical case study, this paper presents an analysis of how cryptocurrency communities emerge, mature and migrate as they make data monies. [ABSTRACT FROM AUTHOR]

Copyright of Stylos is the property of Pontificia Universidad Catolica Argentina and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the era of social networking platforms, user-generated content is flooding every second on online social media platforms like Facebook. So observing and identifying many contents, including threats and sexual harassment, are more accessible than traditional media. Online content with extreme toxicity can lead to online harassment, profanity, personal attacks, and bullying acts. As Bangla is the seventh most spoken language worldwide, the utilization of Bangla language in Facebook has raised current times. The use of abusive comments on Facebook with Bangla also has increased alarmingly, but the research regarding this is very low. In this research work, we concentrate on identifying abusive comments of Bangla language in social media (Facebook) that can filter out at the primitive stage of social media's affixing. To classify abusive comments swiftly and precisely, we apply transformer-based deep neural network models. We employ pre-training language architectures, BERT (Bidirectional Encoder Representations from Transformers) and ELECTRA (Efficiency Learning an Encoder that Classifies Token Replacements Accurately). We have conducted this work with a novel dataset comprises 44,001 comments from multitudinous Facebook posts. In this classification process, we have exhibited an average accuracy, precision, recall, and f1-score to evaluate our proposed models. The outcomes have brought a percipience of our applied BERT and ELECTRA architecture that performs notably with 85.00% and 84.92% test accuracy, respectively. [ABSTRACT FROM AUTHOR]

No Brasil, o mito de Electra foi de interesse de diversos dramaturgos, como no caso de Ivo Bender, ao escrever Bodas ao cair da tarde (1983). Nessa peça, a fim de atender aos moldes de um texto breve de teatro, o mito grego é “reduzido”, condensado em poucas páginas. Mas também é “ampliado”, possibilitando uma nova leitura do conhecido mito da tradição clássica. Com esse propósito, o artigo visa a analisar o mito de Electra presente em Bodas ao cair da tarde, levando em considerações as principais mudanças e inovações empreendidas por Ivo Bender no processo de reescritura.

Hackers are increasingly launching phishing attacks via SMS and social media. Games and dating apps introduce yet another attack vector. However, current deep learning-based phishing detection applications are not applicable to mobile devices due to the computational burden. We propose a lightweight phishing detection algorithm that distinguishes phishing from legitimate websites solely from URLs to be used in mobile devices. As a baseline performance, we apply Artificial Neural Networks (ANNs) to URL-based and HTML-based website features. A model search results in 15 ANN models with accuracies >96%, comparable to state-of-the-art approaches. Next, we test the performance of deep ANNs on URL-based features only; however, all models perform poorly with the highest accuracy of 86.2%, indicating that URL-based features alone are not adequate to detect phishing websites even with deep ANNs. Since language transformers learn to represent context-dependent text sequences, we hypothesize that they will be able to learn directly from the text in URLs to distinguish between legitimate and malicious websites. We apply two state-of-the-art deep transformers (BERT and ELECTRA) for phishing detection. Testing custom and standard vocabularies, we find that pre-trained transformers available for immediate use (with fine-tuning) outperform the model trained with the custom URL-based vocabulary. Using pre-trained transformers to predict phishing websites from only URLs has four advantages: 1) requires little training time (~8 minutes), 2) is more easily updatable than feature-based approaches because no pre-processing of URLs is required, 3) is safer to use because phishing websites can be predicted without physically visiting the malicious sites and 4) is easily deployable for real-time detection and is applicable to run on mobile devices. [ABSTRACT FROM AUTHOR]

Copyright of Human Review is the property of Eagora Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In Greece, the systematic production of ancient drama at the National Theatre, especially after the inauguration of the Epidauria Festival in the 1950s, introduced and recycled a largely ‘classicist’ interpretative and performative model – and this constant recycling ritualized, in turn, its own continuity, gradually establishing what was taken to be the “authentic” performative code, indeed a ‘native’ one, ‘faithful’ to the original texts, meanings, heroes etc. Since the 1980s, performative codes have become more pluralistic and yet the interpretative codes remain essentially classicist, promoting a hero-worshipping theatre of ‘admiration’. Taking as its starting point the first performance of Greek Tragedy directed by a foreign director at the Greek National Theatre, Peter Stein’s Electra by Sophocles, in 2007, the paper discusses various European and Greek performances of the play, in order to show that this classicism permeates the modern Greeks’ overall understanding of ancient Greek culture –the common knowledge of Antiquity– that is configured by/in contemporary Greek consciousness, in order to serve the idea (and the ideology) of a ‘native’ continuity with the Ancient Greek past.

Entre los estudiosos de Galdós es muy conocido todo lo relacionado con el estreno de Electra: la convulsión que produjo en la opinión pública y la reacción desde ámbitos clericales. Sin embargo, no se han mencionado aún las cartas que José Ferrándiz—el entonces 'famoso cura Ferrándiz', olvidado inmediatamente tras su muerte—dirigió al escritor canario. En los últimos años se han descubierto algunos seudónimos usados por este clérigo en rebeldía. Las cartas escritas a Galdós junto con los textos publicados bajo esos seudónimos, permiten comprender en qué medida y por qué el escritor recibió asesoramiento canónico de Ferrándiz tras la publicación de Electra y ayudan a dibujar la relación que surgió entre ambos. Además, en un contexto político y cultural de disputa anticlerical, esos textos ofrecen luz en torno al posicionamiento de Galdós y al papel que desempeñó en él. Se ofrece también la transcripción de las cartas. [ABSTRACT FROM AUTHOR]

The article deals with three euripidean passages (from Electra, Iphigenia among the Taurians and Helen) in which the enactment of ritual actions (such as the admission of a newborn child to the familial group, the celebration of a funerary rite, the purification of a murderer) works as a deceiving or misleading resource. In such circumstances rites play a major dramatic role in creating a complicity between the author, the audience and the characters acting on scene. [ABSTRACT FROM AUTHOR]

In our research we have created a text summarization software tool for Hungarian using multilingual and Hungarian BERT-based models. Two types of text summarization method exist: abstractive and extractive. The abstractive summarization is more similar to human generated summarization. Target summaries may include phrases that the original text does not necessarily contain. This method generates the summarized text by applying keywords that were extracted from the original text. The extractive method summarizes the text by using the most important extracted phrases or sentences from the original text. In our research we have built both abstractive and extractive models for Hungarian. For abstractive models, we have used a multilingual BERT model and Hungarian monolingual BERT models. For extractive summarization, in addition to the BERT models, we have also made experiments with ELECTRA models. We find that the Hungarian monolingual models outperformed the multilingual BERT model in all cases. Furthermore, the ELECTRA small models achieved higher results than some of the BERT models. This result is important because the ELECTRA small models have much fewer parameters and were trained on only 1 GPU within a couple of days. Another important consideration is that the ELECTRA models are much smaller than the BERT models, which is important for the end users. To our best knowledge the first extractive and abstractive summarization systems reported in the present paper are the first such systems for Hungarian. [ABSTRACT FROM AUTHOR]