Character-based Models Research Articles

Embedding Islamic Values in Education: Strategies for Character Building at Madrasah Kulliyatul Mu’allimin Al-Islamiyyah Gontor

The objective of this study is to identify the strategies employed by Madrasah Kulliyatul Mu’allimin Al-Islamiyyah Pondok Modern Darussalam Gontor Ponorogo in the pursuit of enhanced character education and to analyse the impact of these strategies on students’ attitudes, behaviours and achievements. A qualitative approach with a phenomenological research design was employed to gather data through observation, interviews, and documentation. Triangulation was conducted to ensure the validity of the data. The data were subjected to an integrated analysis using the Miles-Huberman model and Mintzberg’s 5P theory. The findings demonstrate that the madrasah effectively employs a range of strategies, including the integration of Islamic values into daily life, character-based learning models, the development of positive habits, leadership training, and the active involvement of parents and the community. The reinforcement of character education has had a beneficial impact on students, facilitating improvements in discipline, responsibility, social conduct, and both academic and non-academic achievements. Additionally, it has led to notable enhancements in leadership and collaboration abilities. This study emphasises the importance of integrating character education into all aspects of madrasah activities and highlights the value of collaboration between madrasahs, parents, and the community in fostering students with robust and autonomous character traits.

Sequence-to-Sequence Models and Their Evaluation for Spoken Language Normalization of Slovenian

Sequence-to-sequence models have been applied to many challenging problems, including those in text and speech technologies. Normalization is one of them. It refers to transforming non-standard language forms into their standard counterparts. Non-standard language forms come from different written and spoken sources. This paper deals with one such source, namely speech from the less-resourced highly inflected Slovenian language. The paper explores speech corpora recently collected in public and private environments. We analyze the efficiencies of three sequence-to-sequence models for automatic normalization from literal transcriptions to standard forms. Experiments were performed using words, subwords, and characters as basic units for normalization. In the article, we demonstrate that the superiority of the approach is linked to the choice of the basic modeling unit. Statistical models prefer words, while neural network-based models prefer characters. The experimental results show that the best results are obtained with neural architectures based on characters. Long short-term memory and transformer architectures gave comparable results. We also present a novel analysis tool, which we use for in-depth error analysis of results obtained by character-based models. This analysis showed that systems with similar overall results can differ in the performance for different types of errors. Errors obtained with the transformer architecture are easier to correct in the post-editing process. This is an important insight, as creating speech corpora is a time-consuming and costly process. The analysis tool also incorporates two statistical significance tests: approximate randomization and bootstrap resampling. Both statistical tests confirm the improved results of neural network-based models compared to statistical ones.

Manajemen Pendidikan Islam Berbasis Karakter di Pondok Pesantren Islahuddini Kediri Lombok Barat

This research aims to explore and analyze the implementation of character-based Islamic education management at the Islahuddin Islamic Boarding School in Kediri and its impact on the formation of the morals and character of the students. The research method used is qualitative research with a descriptive analytical approach. Data was collected through participant observation, in-depth interviews, and document analysis. The results of the research show that the Islahuddin Kediri Islamic Boarding School has succeeded in implementing character-based Islamic education management through structured and integrated programs, including the habituation of Islamic values in daily activities, personality development, and the cultivation of noble character. The impact of this implementation can be seen in increasing moral awareness, responsible attitudes and high social awareness among students. These findings provide an important contribution in the development of character-based Islamic education management models in other Islamic educational institutions.

A search tool based on language modelling developed for The Index of Middle English Prose

Non-standardised early vernaculars present a problem for search tools due to the high degree of variation. The challenge lies in the variation found in orthography, syntax, and lexicon between titles, incipits, and explicits in manuscript copies of the same work. Traditional search methods relying on exact string matching or regular expressions fail to address these variations comprehensively. This project presents a web-based search tool specifically designed to handle linguistic and textual variation. The software is made available as a part of the Index of Middle English Prose (IMEP). The search tool addresses the issue of variation by utilizing a database of incipits and explicits, character-based n-gram language models (LMs) built with the Stanford Research Institute Language Modelling (SRILM) toolkit, and a fuzzy search script (IMEP: FSS) written in Python. The tool optimizes for recall, retrieving multiple potential matches for a search string, without attempting to identify the ‘correct’ one. The search process involves looking up exact matches in the database while simultaneously using the fuzzy search script to evaluate the incipits and explicits against a model of the search string, followed by a match of the search string against models of the incipits and explicits. This two-step process shortens the processing time, which would otherwise be unreasonably long, because while using SRILM to match the search string against each incipit or explicit in the IMEP for precision could be time-consuming, running a first step where all texts are matched against a single LM built from the search string allows for faster processing. A web application, built using Django and Docker, combines the results of the direct database lookup and the fuzzy search script, presenting them as a list with exact matches followed by fuzzy matches ordered by increasing model perplexity. The tool is made available Open Access and can be adapted to other datasets.

A search tool based on language modelling developed for The Index of Middle English Prose.

Non-standardised early vernaculars present a problem for search tools due to the high degree of variation. The challenge lies in the variation found in orthography, syntax, and lexicon between titles, incipits, and explicits in manuscript copies of the same work. Traditional search methods relying on exact string matching or regular expressions fail to address these variations comprehensively. This project presents a web-based search tool specifically designed to handle linguistic and textual variation. The software is made available as a part of the Index of Middle English Prose (IMEP). The search tool addresses the issue of variation by utilizing a database of incipits and explicits, character-based n-gram language models (LMs) built with the Stanford Research Institute Language Modelling (SRILM) toolkit, and a fuzzy search script (IMEP: FSS) written in Python. The tool optimizes for recall, retrieving multiple potential matches for a search string, without attempting to identify the 'correct' one. The search process involves looking up exact matches in the database while simultaneously using the fuzzy search script to evaluate the incipits and explicits against a model of the search string, followed by a match of the search string against models of the incipits and explicits. This two-step process shortens the processing time, which would otherwise be unreasonably long, because while using SRILM to match the search string against each incipit or explicit in the IMEP for precision could be time-consuming, running a first step where all texts are matched against a single LM built from the search string allows for faster processing. A web application, built using Django and Docker, combines the results of the direct database lookup and the fuzzy search script, presenting them as a list with exact matches followed by fuzzy matches ordered by increasing model perplexity. The tool is made available Open Access and can be adapted to other datasets.

Character and moral education based learning in students’ character development

<span lang="EN-US">Internet-based learning is mostly done because of the industrial revolution and COVID-19 so it has an impact on shifting the students’ character. The systematic literature review research purpose was to analyze and provide an overview related to learning based on character and moral education in the student’s character development. Data related to character and moral education (2020-2022) was collected through the Indonesian National Library and Google Scholar for documentation which will then be reviewed. After the screening, 25 articles were selected for analysis using the Miles & Huberman interactive model and thematic analysis to obtain answers to review questions. These findings provided information about various methodologies and research results related to the student’s character and moral education. The results showed that students’ moral character development was influential and related to learning outcomes, self-character, and performance, as well as contributing to students’ mental health. So that efforts can be made in developing and strengthening student character through internal education strategies, such as material content containing character values, local wisdom-based learning, as well as the use of character-based learning models, methods and media, and external strategies in the form of parental support and society.</span>

Local and global character representation enhanced model for Chinese medical named entity recognition

Chinese medical named entity recognition (CMNER) aims to extract entities from Chinese unstructured medical texts. Existing character-based NER models do not comprehensively consider character’s characteristics from different perspectives, which limits their performance in applying to CMNER. In this paper, we propose a local and global character representation enhanced model for CMNER. For the input sentence, the model fuses the spacial and sequential character representation using autoencoder to get the local character representation; extracts the global character representation according to the corresponding domain words; integrates the local and global representation through gating mechanism to obtain the enhanced character representation, which has better ability to perceive medical entities. Finally, the model sent the enhanced character representation to the Bi-LSTM and CRF layers for context encoding and tags decoding respectively. The experimental results demonstrate that our model achieves a significant improvement over the best baseline, increasing the F1 values by 1.04% and 0.62% on the IMCS21 and CMeEE datasets, respectively. In addition, we verify the effectiveness of each component of our model by ablation experiments.

SSMI: Semantic Similarity and Mutual Information Maximization Based Enhancement for Chinese NER

The Chinese NER task consists of two steps, first determining entity boundaries and then labeling them. Some previous work incorporating related words from pre-trained vocabulary into character-based models has been demonstrated to be effective. However, the number of words that characters can match in the vocabulary is large, and their meanings vary widely. It is unreasonable to concatenate all the matched words into the character's representation without making semantic distinctions. This is because words with different semantics also have distinct vectors by the distributed representation. Moreover, mutual information maximization (MIM) provides a unified way to characterize the correction between different granularity of embeddings, we find it can be used to enhance the features in our task. Consequently, this paper introduces a novel Chinese NER model named SSMI based on semantic similarity and MIM. We first match all the potential word boundaries of the input characters from the pre-trained vocabulary and employ BERT to segment the input sentence to get the segmentation containing these characters. After computing their cosine similarity, we obtain the word boundary with the highest similarity and the word group with similarity score larger than a specific threshold. Then, we concatenate the most relevant word boundaries with character vectors. We further calculate the mutual information maximization of group, character and sentence, respectively. Finally, we feed the result from the above steps to our novel network. The results on four Chinese public NER datasets show that our SSMI achieves state-of-the-art performance.

It’s All in the Name: A Character-Based Approach to Infer Religion

AbstractLarge-scale microdata on group identity are critical for studies on identity politics and violence but remain largely unavailable for developing countries. We use personal names to infer religion in South Asia—where religion is a salient social division, and yet, disaggregated data on it are scarce. Existing work predicts religion using a dictionary-based method and, therefore, cannot classify unseen names. We provide character-based machine-learning models that can classify unseen names too with high accuracy. Our models are also much faster and, hence, scalable to large datasets. We explain the classification decisions of one of our models using the layer-wise relevance propagation technique. The character patterns learned by the classifier are rooted in the linguistic origins of names. We apply these to infer the religion of electoral candidates using historical data on Indian elections and observe a trend of declining Muslim representation. Our approach can be used to detect identity groups across the world for whom the underlying names might have different linguistic roots.

Character-Based Thai Word Segmentation with Multiple Attentions

Character-based word segmentation models have been extensively applied to Asian languages, including Thai, owing to their promising performance. These models estimate the word boundaries from a character sequence; however, a Thai character unit in a sequence has no inherent meaning, in contrast with word, subword, and character cluster units that represent more meaningful linguistic information. In this paper, we propose a Thai word segmentation model that uses various types of information, including words, subwords, and character clusters, from a character sequence. Our model applies multiple attentions to refine segmentation inferences by estimating the significant relationships among characters and various unit types. We evaluated our model on three Thai datasets, and the experimental results show that our model outperforms other Thai word segmentation models, demonstrating the validity of using character clusters over subword units. A case study on sample Thai text supported these results. Thus, according to our analysis, particularly the case study, our model can segment Thai text accurately, while other existing models yield incorrect results that violate the Thai writing system.

Applying a Character-Level Model to a Short Arabic Dialect Sentence: A Saudi Dialect as a Case Study

Arabic dialect identification (ADI) has recently drawn considerable interest among researchers in language recognition and natural language processing fields. This study investigated the use of a character-level model that is effectively unrestricted in its vocabulary, to identify fine-grained Arabic language dialects in the form of short written text. The Saudi dialects, particularly the four main Saudi dialects across the country, were considered in this study. The proposed ADI approach consists of five main phases, namely dialect data collection, data preprocessing and labelling, character-based feature extraction, deep learning character-based model/classical machine learning character-based models, and model evaluation performance. Several classical machine learning methods, including logistic regression, stochastic gradient descent, variations of the naive Bayes models, and support vector classification, were applied to the dataset. For the deep learning, the character convolutional neural network (CNN) model was adapted with a bidirectional long short-term memory approach. The collected data were tested under various classification tasks, including two-, three- and four-way ADI tasks. The results revealed that classical machine learning algorithms outperformed the CNN approach. Moreover, the use of the term frequency–inverse document frequency, combined with a character n-grams model ranging from unigrams to four-grams achieved the best performance among the tested parameters.

Computational authorship analysis of the homeric poems

Natural language modeling is used to predict or generate the next word or character of modern languages. Furthermore, statistical character-based language models have been found useful in authorship attribution analyses by studying the linguistic proximity of excerpts unknown to the model. In prior work, we modeled Homeric language and provided empirical findings regarding the authorship nature of the 48 Iliad and Odyssey books. Following this line of work, and considering the current philological views and trends, we break down the two poems further into smaller portions. By employing language modeling we identify outlying passages, indicating reduced linguistic affinity with the main body of the two works and, by extension, potentially different authorship. Our results show that some of the passages isolated as outliers by the language models were also identified as such by human researchers. We further test our methodology and models on texts of similar language and genre created by other authors, namely Hesiod’s “Theogony” and “Work and Days”.

Fake news detection through deep learning techniques

This paper aims to predict whether a given news article is real or fake. We use the dataset available on Kaggle. We then implement several deep learning models (Long short-term Memory (LSTM), Multi-layerPerceptron (MLP), Convolution Neural Networks (CNN), Hybrid CNN-LSTM on this dataset. For these models we examine the effects of character-based vs. word-based models and pretrained embeddings vs. learned embeddings. We also compare the accuracies of various models and report the best accuracy which we would get from a particular model.

Text Mining Based on the Lexicon-Constrained Network in the Context of Big Data

Unstructured textual news data is produced every day; analyzing them using an abstractive summarization algorithm provides advanced analytics to decision-makers. Deep learning network with copy mechanism is finding increasing use in abstractive summarization, because copy mechanism allows sequence-to-sequence models to choose words from the input and put them directly into the output. However, since there is no explicit delimiter in Chinese sentences, most existing models for Chinese abstractive summarization can only perform character copy, resulting in inefficiency. To solve this problem, we propose a lexicon-constrained copying network that models multigranularity in both encoder and decoder. On the source side, words and characters are aggregated into the same input memory using a Transformer-based encoder. On the target side, the decoder can copy either a character or a multicharacter word at each time step, and the decoding process is guided by a word-enhanced search algorithm which facilitates the parallel computation and encourages the model to copy more words. Moreover, we adopt a word selector to integrate keyword information. Experiment results on a Chinese social media dataset show that our model can work standalone or with the word selector. Both forms can outperform previous character-based models and achieve competitive performances.

Robust Botnet DGA Detection: Blending XAI and OSINT for Cyber Threat Intelligence Sharing

We investigated 12 years DNS query logs of our campus network and identified phenomena of malicious botnet domain generation algorithm (DGA) traffic. DGA-based botnets are difficult to detect using cyber threat intelligence (CTI) systems based on blocklists. Artificial intelligence (AI)/machine learning (ML)-based CTI systems are required. This study (1) proposed a model to detect DGA-based traffic based on statistical features with datasets comprising 55 DGA families, (2) discussed how CTI can be expanded with computable CTI paradigm, and (3) described how to improve the explainability of the model outputs by blending explainable AI (XAI) and open-source intelligence (OSINT) for trust problems, an antidote for skepticism to the shared models and preventing automation bias. We define the XAI-OSINT blending as aggregations of OSINT for AI/ML model outcome validation. Experimental results show the effectiveness of our models (96.3% accuracy). Our random forest model provides better robustness against three state-of-the-art DGA adversarial attacks (CharBot, DeepDGA, MaskDGA) compared with character-based deep learning models (Endgame, CMU, NYU, MIT). We demonstrate the sharing mechanism and confirm that the XAI-OSINT blending improves trust for CTI sharing as evidence to validate our proposed computable CTI paradigm to assist security analysts in security operations centers using an automated, explainable OSINT approach (for second opinion). Therefore, the computable CTI reduces manual intervention in critical cybersecurity decision-making.

Character Education in Physical Education Learning Model: A Bibliometric Study on 2011-2020 Scopus Database

Literature shows that character and physical educations, to enhance students' fitness and growth through physical activity, have a vital role in the learning process. A character-based physical education learning model is required to integrate the two educational ideas. A study on the development of research on this topic is required for the model's application and development. Therefore, this study aims to find and analyze articles in Scopus indexed journals of the last decade (2011-2020) related to character-based physical education learning models. In this study, a bibliometric analysis was employed to explore the roadmap for character-based physical education learning. This bibliometric study has four steps: (1) finding related articles, (2) filtering, (3) validating and completing the article information, and (4) carrying out a bibliometric analysis. This study discovered eight findings, including: (1) publication trend of the physical education learning model in 2011-2020; (2) citation number of the article; (3) author collaboration; (4) the most used keywords by the authors; (5) abstract analysis; (6) institutional collaboration; (7) country analysis; and (8) analysis of character values promoted in the bibliography. Based on these eight findings, this study concludes that academics and researchers pay insufficient attention to character-based physical education learning models. This also suggests that in the context of physical education learning, their attention is more concentrated on the cognitive and psychomotor domains. On the other hand, academics have not paid much attention to character as an effective area. This finding needs to be highlighted because, in education, besides knowledge, an educator has a duty to transfer values. Therefore, more publications on the integration of character education into physical education are required. This study can assist in mapping future research directions that will encourage further research on physical education.

Character-based 4C Learning Model to Improving Students' Metacognitive Abilities: A Develop Phase of Research & Development

This research aims to determine the level of validity, practicality, and effectiveness (develop phase) development of character-based 4C learning models to improve students' metacognitive abilities. This research focuses on the develop phase of the 4D theory (Define, Design, Develop and Disseminate) by Thiagarajan, Semmel, & Semmel (1974). The develop phase consists of validity testing by experts, practicality testing by lecturers, and effectiveness testing by students. The subjects of this research were 16 students and 2 lecturers of the Primary School Teacher Education Research Program (PGSD) STKIP Andi Matappa, Pangkep Regency. In addition, two validators were also selected as participants to assess the validity of this research product. The data collection techniques used was validation sheet, questionnaire, and tests. The collected data were analyzed using a quantitative approach with the help of SPSS 23.00. The results showed that the research products in the form of model books and character-based 4C learning tools were declared valid, practical, and effective and could be used by lecturers to teach Pancasila and Citizenship Education courses.

VCD Development of Innovative Character-Based Learning Models as Learning Media in Learning Strategy Courses

This research aims to develop VCD media on character-based innovative learning models. The type of this research is the study of R & D with Four-D). The analysis of the data used to develop the models of learning and development within the VCD pieces is using the sheet media expert assessment and experts’ and students’ responses. Based on the evaluation through questionnaires by material experts showed 87.0% for character-based PBL Learning plan and got 85.9% for Cooperative Learning Model type TS-TS, both including its category Neither instrument of Lesson Plan. Results of the validation study model VCD by a media expert with the details of the quantitative results are obtained to have an average percentage of 84.70% for VCD character-based PBL learning model and 88.2% for the type of cooperative learning model TS-TS. From these results, it can be concluded that the media VCD learning model being developed has fulfilled the good criterion. Meanwhile, based on student questionnaires obtained quantitative data has a percentage of 80.60% for VCD on character-based PBL learning model and 84.7% for the type of cooperative learning model TS-TS. Therefore, it can be concluded that the developed media is already categorized to be good.

Character-Level Neural Language Modelling in the Clinical Domain.

Word embeddings have become the predominant representation scheme on a token-level for various clinical natural language processing (NLP) tasks. More recently, character-level neural language models, exploiting recurrent neural networks, have again received attention, because they achieved similar performance against various NLP benchmarks. We investigated to what extent character-based language models can be applied to the clinical domain and whether they are able to capture reasonable lexical semantics using this maximally fine-grained representation scheme. We trained a long short-term memory network on an excerpt from a table of de-identified 50-character long problem list entries in German, each of which assigned to an ICD-10 code. We modelled the task as a time series of one-hot encoded single character inputs. After the training phase we accessed the top 10 most similar character-induced word embeddings related to a clinical concept via a nearest neighbour search and evaluated the expected interconnected semantics. Results showed that traceable semantics were captured on a syntactic level above single characters, addressing the idiosyncratic nature of clinical language. The results support recent work on general language modelling that raised the question whether token-based representation schemes are still necessary for specific NLP tasks.

Publicly available machine learning models for identifying opioid misuse from the clinical notes of hospitalized patients

BackgroundAutomated de-identification methods for removing protected health information (PHI) from the source notes of the electronic health record (EHR) rely on building systems to recognize mentions of PHI in text, but they remain inadequate at ensuring perfect PHI removal. As an alternative to relying on de-identification systems, we propose the following solutions: (1) Mapping the corpus of documents to standardized medical vocabulary (concept unique identifier [CUI] codes mapped from the Unified Medical Language System) thus eliminating PHI as inputs to a machine learning model; and (2) training character-based machine learning models that obviate the need for a dictionary containing input words/n-grams. We aim to test the performance of models with and without PHI in a use-case for an opioid misuse classifier.MethodsAn observational cohort sampled from adult hospital inpatient encounters at a health system between 2007 and 2017. A case-control stratified sampling (n = 1000) was performed to build an annotated dataset for a reference standard of cases and non-cases of opioid misuse. Models for training and testing included CUI codes, character-based, and n-gram features. Models applied were machine learning with neural network and logistic regression as well as expert consensus with a rule-based model for opioid misuse. The area under the receiver operating characteristic curves (AUROC) were compared between models for discrimination. The Hosmer-Lemeshow test and visual plots measured model fit and calibration.ResultsMachine learning models with CUI codes performed similarly to n-gram models with PHI. The top performing models with AUROCs > 0.90 included CUI codes as inputs to a convolutional neural network, max pooling network, and logistic regression model. The top calibrated models with the best model fit were the CUI-based convolutional neural network and max pooling network. The top weighted CUI codes in logistic regression has the related terms ‘Heroin’ and ‘Victim of abuse’.ConclusionsWe demonstrate good test characteristics for an opioid misuse computable phenotype that is void of any PHI and performs similarly to models that use PHI. Herein we share a PHI-free, trained opioid misuse classifier for other researchers and health systems to use and benchmark to overcome privacy and security concerns.