Search results

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.

This study aims to establish a model for rapid and accurate emotion recognition in restaurant online reviews, thus advancing the literature and providing practical insights into electronic word-of-mouth management for the industry.

This study elaborates a hybrid model that integrates deep learning (DL) and a sentiment lexicon (SL) and compares it to five other models, including SL, random forest (RF), naïve Bayes, support vector machine (SVM) and a DL model, for the task of emotion recognition in restaurant online reviews. These models are trained and tested using 652,348 online reviews from 548 restaurants.

The hybrid approach performs well for valence-based emotion and discrete emotion recognition and is highly applicable for mining online reviews in a restaurant setting. The performances of SL and RF are inferior when it comes to recognizing discrete emotions. The DL method and SVM can perform satisfactorily in the valence-based emotion recognition.

These findings provide methodological and theoretical implications; thus, they advance the current state of knowledge on emotion recognition in restaurant online reviews. The results also provide practical insights into intelligent service quality monitoring and electronic word-of-mouth management for the industry.

This study proposes a superior model for emotion recognition in restaurant online reviews. The methodological framework and steps are elucidated in detail for future research and practical application. This study also details the performances of other commonly used models to support the selection of methods in research and practical applications.

This paper aims to determine the adaptability of China’s legal system in recognizing and enforcing foreign judgements in China.

Academic articles, case law and books are examined as are relevant reports by various regulatory authorities and organizations.

Historically, Chinese courts have strictly adhered to “de facto reciprocity”, which made it difficult for foreign judgements to be recognized and enforced in China. Fortunately, Chinese courts have since abandoned their rigid adherence to de facto reciprocity, and have instead, used flexible tests of reciprocity such as de jure reciprocity, reciprocal commitment and reciprocal understand/consensus. Accordingly, this would facilitate the recovery of stolen assets, as there is a lower threshold for the recognition and enforcement of a foreign judgement.

There are limited data available in relation to the recognition and enforcement of foreign judgements pertaining to the recovery of stolen assets. Any discussions within this paper are based on the impressionistic observations of this author, which may not reflect the true state of affairs within the Belt and Road Initiative.

Those who are interested in examining the viability in recognizing and enforcing foreign judgements relating to stolen assets will have an interest in this topic.

The value of the paper is to demonstrate the difficulties in recognizing and enforcing foreign judgements in China in relation to stolen assets.

This research aimed to visualize and analyze the co-word network and thematic clusters of the intellectual structure in the field of linked data during 1900–2021.

This applied research employed a descriptive and analytical method, scientometric indicators, co-word techniques, and social network analysis. VOSviewer, SPSS, Python programming, and UCINet software were used for data analysis and network structure visualization.

The top ranks of the Web of Science (WOS) subject categorization belonged to various fields of computer science. Besides, the USA was the most prolific country. The keyword ontology had the highest frequency of co-occurrence. Ontology and semantic were the most frequent co-word pairs. In terms of the network structure, nine major topic clusters were identified based on co-occurrence, and 29 thematic clusters were identified based on hierarchical clustering. Comparisons between the two clustering techniques indicated that three clusters, namely semantic bioinformatics, knowledge representation, and semantic tools were in common. The most mature and mainstream thematic clusters were natural language processing techniques to boost modeling and visualization, context-aware knowledge discovery, probabilistic latent semantic analysis (PLSA), semantic tools, latent semantic indexing, web ontology language (OWL) syntax, and ontology-based deep learning.

This study adopted various techniques such as co-word analysis, social network analysis network structure visualization, and hierarchical clustering to represent a suitable, visual, methodical, and comprehensive perspective into linked data.

Employee recognition systems are ubiquitous in organizations (WorldatWork, 2019) and have positive effects on work outcomes (e.g. Stajkovic and Luthans, 2001). However, psychologically meaningful recognition relies on the recognition giver being motivated to observe and recognize coworkers. Crises such as the COVID-19 pandemic may impact recognition giving in varying ways, yet little research considers this possibility.

This longitudinal field study examined the impact of the COVID-19 crisis on recognition and acknowledgment giving among frontline and nonfrontline healthcare workers at daily and aggregated levels. We tested the relationships between publicly available daily indicators of COVID-19 and objectively measured daily recognition and acknowledgment giving within a web-based platform.

We found that the amount of daily recognition giving was no different during the crisis compared to the year before, but fewer employees gave recognition, and significantly more recognition was given on days when COVID-19 indicators were relatively high. In contrast, the amount of acknowledgment giving was significantly lower in frontline staff and significantly higher in nonfrontline staff during the pandemic than before, but on a daily-level, acknowledgment was unrelated to COVID-19 indicators.

Our results suggest that organizational crises may at once inhibit and stimulate employee recognition and acknowledgment.

Our research is the first to empirically demonstrate that situational factors associated with a crisis can impact recognition giving behavior, and they do so in ways consistent with ostensibly contradictory theories.

Based on the perspectives of social capital, image motivation and motivation affordances, this paper explores the direct and moderation effects of different kinds of motivations (i.e. relationship-based motivation, community-based motivation and individual-based motivation) on users' continuous knowledge contributions in social question and answer (Q&A) communities.

The authors collect the panel data of 10,193 users from a popular social Q&A community in China. Then, a negative binomial regression model is adopted to analyze the collected data.

The paper demonstrates that social learning, peer recognition and knowledge seeking positively affect users' continuous contribution behaviors. However, the results also show that social exposure has the opposite effect. In addition, self-presentation is found to moderate the influence of social factors on users' continuous use behaviors, while the moderation effect of motivation affordances has no significance.

First, this study develops a comprehensive motivation framework that helps gain deeper insights into the underlying mechanism of knowledge contribution in social Q&A communities. Second, this study conducts panel data analysis to capture the impacts of motivations over time, rather than intentions at a fixed time point. Third, the findings can help operators of social Q&A communities to optimize community norms and incentive mechanisms.

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.

It is imperative for policymakers, financial institutions, and individual investors to comprehend the factors that impact stock market participation, given the growing significance of the stock market in terms of personal and national wealth. This study endeavours to explore the relationship between cognitive ability and participation in the stock market. We examine the relationship between cognitive abilities and stock market participation, and further explore the mechanism of their influence.

The data from the China Family Panel Studies is utilized, and Tobit and Probit regressions are employed. Additionally, an instrumental variable approach (IV-estimate) is implemented to address the endogeneity issue linked to cognitive ability, and the study’s findings are resilient.

The results reveal a significant positive relationship between cognitive ability and stock market participation. Additionally, the findings suggest that households with higher cognitive ability tend to aggregate more information, expand social networks, and take more risks. A likely explanation is that individuals with higher cognitive ability are more likely to process more external information and evaluate the subjective uncertainty of stock markets based on a well-defined probability distribution. Our findings indicate that the impact of cognitive ability on stock market participation varies among families with differing education levels, genders, marital statuses, and geographical locations.

Therefore, the roles of cognitive abilities in accelerating stock market participation should be fully considered. More information channels and sources that contain financial markets’ information (e.g. mobile applications and financial education) should be provided. Thus, the significance of cognitive ability in increasing stock market participation should be fully considered. Providing more information channels and sources, such as mobile applications and financial education, that contain financial markets’ information would be helpful. Our study contributes to promoting financial literacy and inclusion by highlighting the significant positive impact of cognitive ability, where institutions can tailor their outreach efforts and information channels to better serve individuals with different cognitive ability.

Many students are found facing difficulties in learning English due to plenty of reasons: known and unknown ones. In order to overcome such an issue, the instructors have to explore for effective techniques of teaching English to motivate learners by any means. Technology in general and informatics in particular can be thought of as innovative tool of pedagogy in the current teaching-learning environment. The present proposal of research aims at creating innovative approaches, which attract learners' interest and catch their attention for better outputs.

Following subsections have been discussed keeping the significance in view. Setting of the study: The present study was conducted at King Abdulaziz University, Jeddah-Saudi Arabia, which is one of the Saudi Arabian universities; however, it has opened up new avenues for the pedagogues, teachers of English and researchers to conduct studies in various allied fields. In order to have a representative sample of students' population, the participants were chosen from the “preparatory year”. Material and tools: This study used a questionnaire (Appendix) and a test to evaluate performances of the two groups: controlled and experimental. In order to further strengthen the findings, semi structured interview was conducted for a few select students from the student-sample. Since the questionnaire was adapted, the statistical validity and reliability was not considered to be essential; however, content/face validity was ensured by consulting 10 experts in the field of education/methods of teaching.

Based on the analysis of data gathered from the test performances of the two groups of students, it was found that there existed a significant difference in the test scores. The questionnaire responses also proved that infographics can be proved to be an interesting tool of education in general and English language teaching in particular. However, it has been noticed from the gathered data that not many teachers are comfortable using multimedia or infographics for different reasons. The results of the present study are in line with the study by Rezaei and Sayadian (2015) that support the idea of infographics that would help English teachers to develop understanding and insights to design among the learners. They further contend that the infographic instruction offers choices for the utilization of collaborative activities. In addition, the infographics enhance students' performance as a whole as also supported by Alrwele (2017).

The study was conducted on a small sample which might affect the generalization of the outcomes. It was carried out with special reference to teaching of vocabulary and reading.

There can be many recommendations for different stakeholders. For teachers, it is recommended that they should know about the significance of infographs for catching the attention of students. They should know how to design interesting and colorful infographs. The administration/management should facilitate the teachers with the required software or platform to create infographics and integrate in an English language class. In addition, teachers should attend workshops and training courses organized for topics related to the infographs.

The author checked the study for plagiarism (excluding references) and found it to be 93% plagiarism free.

This paper aims to systematically visualize the structure and trends from 2005 to 2021, which will help scholars gain a deeper appreciation for existing studies and grasp future research possibilities and directions.

The approach is bibliometric, using VOSviewer and CiteSpace to analyze 765 journal articles and reviews from the Web of Science (WoS) and Scopus databases over the past 16 years.

There is considerable interest in urban tourism destination image (U-TDI), partly because of the role of image in promoting the economic development of urban tourism and the associated benefits to stakeholders. Most research output concerns China, the USA, Spain and the United Kingdom (UK); research in the USA context has had a particularly wide range of influence. Highly cited journals play a crucial role, while subject structure, key articles and high-frequency keywords indicate popular topics, sub-themes and development trends. Drawing on these findings, the authors identify four topics that deserve further study.

This systematic review will enhance understanding of U-TDI research and inform future research directions as well as highlighting the need to explore destination image in greater depth, it guides policymakers in the tourism industry seeking to develop city image.