Search results

This paper aims to investigate how congruent keywords are used in information security policies (ISPs) to pinpoint and guide clear actionable advice and suggest a metric for measuring the quality of keyword use in ISPs.

A qualitative content analysis of 15 ISPs from public agencies in Sweden was conducted with the aid of Orange Data Mining Software. The authors extracted 890 sentences from these ISPs that included one or more of the analyzed keywords. These sentences were analyzed using the new metric – keyword loss of specificity – to assess to what extent the selected keywords were used for pinpointing and guiding actionable advice. Thus, the authors classified the extracted sentences as either actionable advice or other information, depending on the type of information conveyed.

The results show a significant keyword loss of specificity in relation to pieces of actionable advice in ISPs provided by Swedish public agencies. About two-thirds of the sentences in which the analyzed keywords were used focused on information other than actionable advice. Such dual use of keywords reduces the possibility of pinpointing and communicating clear, actionable advice.

The suggested metric provides a means to assess the quality of how keywords are used in ISPs for different purposes. The results show that more research is needed on how keywords are used in ISPs.

The authors recommended that ISP designers exercise caution when using keywords in ISPs and maintain coherency in their use of keywords. ISP designers can use the suggested metrics to assess the quality of actionable advice in their ISPs.

The keyword loss of specificity metric adds to the few quantitative metrics available to assess ISP quality. To the best of the authors’ knowledge, applying this metric is a first attempt to measure the quality of actionable advice in ISPs.

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

Aspect-based sentiment analysis (ASA) is a task of sentiment analysis that requires predicting aspect sentiment polarity for a given sentence. Many traditional techniques use graph-based mechanisms, which reduce prediction accuracy and introduce large amounts of noise. The other problem with graph-based mechanisms is that for some context words, the feelings change depending on the aspect, and therefore it is impossible to draw conclusions on their own. ASA is challenging because a given sentence can reveal complicated feelings about multiple aspects.

This research proposed an optimized attention-based DL model known as optimized aspect and self-attention aware long short-term memory for target-based semantic analysis (OAS-LSTM-TSA). The proposed model goes through three phases: preprocessing, aspect extraction and classification. Aspect extraction is done using a double-layered convolutional neural network (DL-CNN). The optimized aspect and self-attention embedded LSTM (OAS-LSTM) is used to classify aspect sentiment into three classes: positive, neutral and negative.

To detect and classify sentiment polarity of the aspect using the optimized aspect and self-attention embedded LSTM (OAS-LSTM) model. The results of the proposed method revealed that it achieves a high accuracy of 95.3 per cent for the restaurant dataset and 96.7 per cent for the laptop dataset.

The novelty of the research work is the addition of two effective attention layers in the network model, loss function reduction and accuracy enhancement, using a recent efficient optimization algorithm. The loss function in OAS-LSTM is minimized using the adaptive pelican optimization algorithm, thus increasing the accuracy rate. The performance of the proposed method is validated on four real-time datasets, Rest14, Lap14, Rest15 and Rest16, for various performance metrics.

English as a foreign langauge (EFL) students find it difficult to apply the theoretical knowledge they acquire on translation in the practical world. Therefore, this study explored if training in pretranslation techniques (PTTs) (syntactic parsing) as suggested by Almanna (2018) could improve the translation proficiency of Yemeni EFL students. Moreover, the study also assessed which of the PTTs the intervention helped to develop.

The study adopted a primarily experimental pre- and posttests research design, and the sample comprised of an intake class with 16 students enrolled in the fourth year, Bachelor in Education (B.Ed), Hadhramout University. Six participants were also interviewed to gather the students' perceptions on using PTTs.

Results showed that students' performance in translation developed significantly (Sig. = 0.002). All the six PTTs showed development, though subject, tense and aspect developed more significantly (Sig. = 0.034, 0.002, 0.001 respectively). Finally, the study reported students' positive perceptions on the importance of using PTTs before doing any translation tasks.

One of the recurrent errors that can be noticed in Yemeni EFL students' production is their inability to transfer the grammatical elements of sentences from L1 (Arabic) into L2 (English) or the visa versa. The researchers thought though translation is more than the syntactic transmission of one language into another, analyzing the elements of sentences using syntactic and semantic parsing can help students to produce acceptable texts in the target language. These claims would be proved or refuted after analyzing the experiment result of the present study.

The framework of this paper is financial mathematics and, more specifically, the control of data fraud and manipulation with their subsequent economic effects, namely, in financial markets. The purpose of this paper is to calculate the global loss or gain, which supposes, for the borrower, a change of the interest rate while the contracted loan is in force or, in another case, the loan has finished.

The methodology used in this work has been, in the first place, a review of the existing literature on the topic of manipulability and abusiveness of the loan interest rates applied by banks; in the second place, the introduction of a mathematical-financial analysis to calculate the interests paid in excess; and, finally, the compilation of several sentences issued on the application of the so-called mortgage loan reference index (MLRI) to mortgage loans in Spain.

There are three main contributions in this paper. First, the calculation of the interests paid in excess in the amortization of mortgage loans referenced to an overvalued interest rate. Second, an empirical application shows the amount to be refunded to a Spanish consumer when amortizing his/her mortgage loan referenced to the MLRI instead of the Euro InterBank Offered Rate (EURIBOR). Third, consideration has been made to the effects and the possible solutions to the legal problems arising from this type of contract.

This research is a useful tool capable of implementing the financial calculation needed to find out overpaid interests in mortgage loans and to execute the sentences dealing with this topic. However, a limitation of this study is the lack of enough sentences on mortgage loans referenced to the MLRI to get some additional information about the number of borrowers affected by these legal sentences and the amount refunded by the financial institutions.

To the best of the authors’ knowledge, this is the first time that deviations in the payment of interests have been calculated when amortizing a mortgage.

Advanced big data analysis and machine learning methods are concurrently used to unleash the value of the data generated by government hotline and help devise intelligent applications including automated process management, standard construction and more accurate dispatched orders to build high-quality government service platforms as more widely data-driven methods are in the process.

In this study, based on the influence of the record specifications of texts related to work orders generated by the government hotline, machine learning tools are implemented and compared to optimize classify dispatching tasks by performing exploratory studies on the hotline work order text, including linguistics analysis of text feature processing, new word discovery, text clustering and text classification.

The complexity of the content of the work order is reduced by applying more standardized writing specifications based on combining text grammar numerical features. So, order dispatch success prediction accuracy rate reaches 89.6 per cent after running the LSTM model.

The proposed method can help improve the current dispatching processes run by the government hotline, better guide staff to standardize the writing format of work orders, improve the accuracy of order dispatching and provide innovative support to the current mechanism.

The number of construction dispute cases has maintained a high growth trend in recent years. The effective exploration and management of construction contract risk can directly promote the overall performance of the project life cycle. The miss of clauses may result in a failure to match with standard contracts. If the contract, modified by the owner, omits key clauses, potential disputes may lead to contractors paying substantial compensation. Therefore, the identification of construction project contract missing clauses has heavily relied on the manual review technique, which is inefficient and highly restricted by personnel experience. The existing intelligent means only work for the contract query and storage. It is urgent to raise the level of intelligence for contract clause management. Therefore, this paper aims to propose an intelligent method to detect construction project contract missing clauses based on Natural Language Processing (NLP) and deep learning technology.

A complete classification scheme of contract clauses is designed based on NLP. First, construction contract texts are pre-processed and converted from unstructured natural language into structured digital vector form. Following the initial categorization, a multi-label classification of long text construction contract clauses is designed to preliminary identify whether the clause labels are missing. After the multi-label clause missing detection, the authors implement a clause similarity algorithm by creatively integrating the image detection thought, MatchPyramid model, with BERT to identify missing substantial content in the contract clauses.

1,322 construction project contracts were tested. Results showed that the accuracy of multi-label classification could reach 93%, the accuracy of similarity matching can reach 83%, and the recall rate and F1 mean of both can reach more than 0.7. The experimental results verify the feasibility of intelligently detecting contract risk through the NLP-based method to some extent.

NLP is adept at recognizing textual content and has shown promising results in some contract processing applications. However, the mostly used approaches of its utilization for risk detection in construction contract clauses predominantly are rule-based, which encounter challenges when handling intricate and lengthy engineering contracts. This paper introduces an NLP technique based on deep learning which reduces manual intervention and can autonomously identify and tag types of contractual deficiencies, aligning with the evolving complexities anticipated in future construction contracts. Moreover, this method achieves the recognition of extended contract clause texts. Ultimately, this approach boasts versatility; users simply need to adjust parameters such as segmentation based on language categories to detect omissions in contract clauses of diverse languages.

The research on structure function recognition mainly concentrates on identifying a specific part of academic literature and its applicability in the multidiscipline perspective. A specific part of academic literature, such as sentences, paragraphs and chapter contents are also called a level of academic literature in this paper. There are a few comparative research works on the relationship between models, disciplines and levels in the process of structure function recognition. In view of this, comparative research on structure function recognition based on deep learning has been conducted in this paper.

An experimental corpus, including the academic literature of traditional Chinese medicine, library and information science, computer science, environmental science and phytology, was constructed. Meanwhile, deep learning models such as convolutional neural networks (CNN), long and short-term memory (LSTM) and bidirectional encoder representation from transformers (BERT) were used. The comparative experiments of structure function recognition were conducted with the help of the deep learning models from the multilevel perspective.

The experimental results showed that (1) the BERT model performed best, with F1 values of 78.02, 89.41 and 94.88%, respectively at the level of sentence, paragraph and chapter content. (2) The deep learning models performed better on the academic literature of traditional Chinese medicine than on other disciplines in most cases, e.g. F1 values of CNN, LSTM and BERT, respectively arrived at 71.14, 69.96 and 78.02% at the level of sentence. (3) The deep learning models performed better at the level of chapter content than other levels, the maximum F1 values of CNN, LSTM and BERT at 91.92, 74.90 and 94.88%, respectively. Furthermore, the confusion matrix of recognition results on the academic literature was introduced to find out the reason for misrecognition.

This paper may inspire other research on structure function recognition, and provide a valuable reference for the analysis of influencing factors.

Using a newly compiled corpus module consisting of utterances from Asian learners during L2 English interviews, this study examined how Asian EFL learners' L1s (Chinese, Indonesian, Japanese, Korean, Taiwanese and Thai), their L2 proficiency levels (A2, B1 low, B1 upper and B2+) and speech task types (picture descriptions, roleplays and QA-based conversations) affected four aspects of vocabulary usage (number of tokens, standardized type/token ratio, mean word length and mean sentence length).

Four aspects concern speech fluency, lexical richness, lexical complexity and structural complexity, respectively.

Subsequent corpus-based quantitative data analyses revealed that (1) learner/native speaker differences existed during the conversation and roleplay tasks in terms of the number of tokens, type/token ratio and sentence length; (2) an L1 group effect existed in all three task types in terms of the number of tokens and sentence length; (3) an L2 proficiency effect existed in all three task types in terms of the number of tokens, type-token ratio and sentence length; and (4) the usage of high-frequency vocabulary was influenced more strongly by the task type and it was classified into four types: Type A vocabulary for grammar control, Type B vocabulary for speech maintenance, Type C vocabulary for negotiation and persuasion and Type D vocabulary for novice learners.

These findings provide clues for better understanding L2 English vocabulary usage among Asian learners during speech.

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.

This work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.