Relevant bibliographies by topics / Query suggestions / Journal articles

To see the other types of publications on this topic, follow the link: Query suggestions.

Journal articles on the topic 'Query suggestions'

Author: Grafiati

Published: 5 June 2025

Last updated: 15 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Query suggestions.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

Gao, Wei, Cheng Niu, Jian-Yun Nie, Ming Zhou, Kam-Fai Wong, and Hsiao-Wuen Hon. "Exploiting query logs for cross-lingual query suggestions." ACM Transactions on Information Systems 28, no. 2 (2010): 1–33. http://dx.doi.org/10.1145/1740592.1740594.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Ma, Hao, Michael Lyu, and Irwin King. "Diversifying Query Suggestion Results." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (2010): 1399–404. http://dx.doi.org/10.1609/aaai.v24i1.7514.

Full text

Abstract:

In order to improve the user search experience, Query Suggestion, a technique for generating alternative queries to Web users, has become an indispensable feature for commercial search engines. However, previous work mainly focuses on suggesting relevant queries to the original query while ignoring the diversity in the suggestions, which will potentially dissatisfy Web users' information needs. In this paper, we present a novel unified method to suggest both semantically relevant and diverse queries to Web users. The proposed approach is based on Markov random walk and hitting time analysis on the query-URL bipartite graph. It can effectively prevent semantically redundant queries from receiving a high rank, hence encouraging diversities in the results. We evaluate our method on a large commercial clickthrough dataset in terms of relevance measurement and diversity measurement. The experimental results show that our method is very effective in generating both relevant and diverse query suggestions.

APA, Harvard, Vancouver, ISO, and other styles

Bonart, Malte, Anastasiia Samokhina, Gernot Heisenberg, and Philipp Schaer. "An investigation of biases in web search engine query suggestions." Online Information Review 44, no. 2 (2019): 365–81. http://dx.doi.org/10.1108/oir-11-2018-0341.

Full text

Abstract:

Purpose Survey-based studies suggest that search engines are trusted more than social media or even traditional news, although cases of false information or defamation are known. The purpose of this paper is to analyze query suggestion features of three search engines to see if these features introduce some bias into the query and search process that might compromise this trust. The authors test the approach on person-related search suggestions by querying the names of politicians from the German Bundestag before the German federal election of 2017. Design/methodology/approach This study introduces a framework to systematically examine and automatically analyze the varieties in different query suggestions for person names offered by major search engines. To test the framework, the authors collected data from the Google, Bing and DuckDuckGo query suggestion APIs over a period of four months for 629 different names of German politicians. The suggestions were clustered and statistically analyzed with regards to different biases, like gender, party or age and with regards to the stability of the suggestions over time. Findings By using the framework, the authors located three semantic clusters within the data set: suggestions related to politics and economics, location information and personal and other miscellaneous topics. Among other effects, the results of the analysis show a small bias in the form that male politicians receive slightly fewer suggestions on “personal and misc” topics. The stability analysis of the suggested terms over time shows that some suggestions are prevalent most of the time, while other suggestions fluctuate more often. Originality/value This study proposes a novel framework to automatically identify biases in web search engine query suggestions for person-related searches. Applying this framework on a set of person-related query suggestions shows first insights into the influence search engines can have on the query process of users that seek out information on politicians.

APA, Harvard, Vancouver, ISO, and other styles

Momtazi, Saeedeh, and Fabian Lindenberg. "Generating query suggestions by exploiting latent semantics in query logs." Journal of Information Science 42, no. 4 (2015): 437–48. http://dx.doi.org/10.1177/0165551515594723.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Kruschwitz, Udo, Deirdre Lungley, M.-Dyaa Albakour, and Dawei Song. "Deriving query suggestions for site search." Journal of the American Society for Information Science and Technology 64, no. 10 (2013): 1975–94. http://dx.doi.org/10.1002/asi.22901.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Klungre, Vidar N., Ahmet Soylu, Ernesto Jimenez-Ruiz, Evgeny Kharlamov, and Martin Giese. "Query Extension Suggestions for Visual Query Systems Through Ontology Projection and Indexing." New Generation Computing 37, no. 4 (2019): 361–92. http://dx.doi.org/10.1007/s00354-019-00071-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Pillai, Anuradha. "Query Recommendation System in Social Networks." Journal of Management and Service Science (JMSS) 2, no. 2 (2022): 1–20. http://dx.doi.org/10.54060/jmss.2022.20.

Full text

Abstract:

Recommender Systems are software which provides suggestions to the user according to his or her interest. These suggestions are related to supporting users in making their decisions, for example, what to search, what to buy, what to listen, etc. Recommender systems are very important in online stores where there are a lot of items to buy. These recommender systems help user to find things according to their interest and buy them. There are a lot of techniques proposed for recommendation and used in commercial environments. People are thought to trust suggestions from friends more than those from websites that are similar to them [2]. As a result, it is helpful to feed a recommender system with the friends' ratings. However, social media sharing websites' recommender systems have several difficulties, such as ranking the information from the user's friends as well, finding information from other sources in comparison to the user's immediate friends, and using metadata and context links for suggestion. In this research, an architecture based on profile-based crawling of social media sharing websites is proposed for query recommendation.

APA, Harvard, Vancouver, ISO, and other styles

Niu, Xi, and Diane Kelly. "The use of query suggestions during information search." Information Processing & Management 50, no. 1 (2014): 218–34. http://dx.doi.org/10.1016/j.ipm.2013.09.002.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Chen, Wanyu, Zepeng Hao, Taihua Shao, and Honghui Chen. "Personalized query suggestion based on user behavior." International Journal of Modern Physics C 29, no. 04 (2018): 1850036. http://dx.doi.org/10.1142/s0129183118500365.

Full text

Abstract:

Query suggestions help users refine their queries after they input an initial query. Previous work mainly concentrated on similarity-based and context-based query suggestion approaches. However, models that focus on adapting to a specific user (personalization) can help to improve the probability of the user being satisfied. In this paper, we propose a personalized query suggestion model based on users’ search behavior (UB model), where we inject relevance between queries and users’ search behavior into a basic probabilistic model. For the relevance between queries, we consider their semantical similarity and co-occurrence which indicates the behavior information from other users in web search. Regarding the current user’s preference to a query, we combine the user’s short-term and long-term search behavior in a linear fashion and deal with the data sparse problem with Bayesian probabilistic matrix factorization (BPMF). In particular, we also investigate the impact of different personalization strategies (the combination of the user’s short-term and long-term search behavior) on the performance of query suggestion reranking. We quantify the improvement of our proposed UB model against a state-of-the-art baseline using the public AOL query logs and show that it beats the baseline in terms of metrics used in query suggestion reranking. The experimental results show that: (i) for personalized ranking, users’ behavioral information helps to improve query suggestion effectiveness; and (ii) given a query, merging information inferred from the short-term and long-term search behavior of a particular user can result in a better performance than both plain approaches.

APA, Harvard, Vancouver, ISO, and other styles

Halimah Tus Sadiah, Lia Dahlia Iryani, Tjut Awaliyah Zuraiyah, Yuli Wahyuni, and Cantika Zaddana. "Implementation of Levenshtein Distance Algorithm for Product Search Query Suggestions on Koro Pedang Edutourism E-Commerce." Journal of Advanced Research in Applied Sciences and Engineering Technology 42, no. 2 (2024): 188–96. http://dx.doi.org/10.37934/araset.42.2.188196.

Full text

Abstract:

Users sometimes write queries that are inaccurate or typos in the product search contained in the Koro Pedang Educational Tourism e-commerce, so the system is not find product search results because the query entered in the system is incorrect. This can frustrate users because they cannot find the product they are looking for, so the users leave the website. According to these problems, it is necessary to suggest a query on the product search function. This is expected to assist users in finding the product they are looking for if there is an error in typing the query. This research purposes were to implement the Levenshtein Distance Algorithm for product search query suggestions on Koro Pedang Educational Tourism e-commerce. The stages of this research, namely the development of the search module, implementation of the Levenshtein Distance Algorithm and testing. The implementation of the Levenshtein Distance Algorithm in the search function for Koro Pedang Educational Tourism e-commerce products, a Suggestion Query is generated for Query typos in the search function with an accuracy value of 90%, Precision 95% and Recall 90.9%. This shows that the performance of the algorithm that has been applied to the search function for query suggestion is very good. The application of the Levenshtein Distance Algorithm gives a positive value to the usability of searching for e-commerce products for Koro Pedang Educational Tourism.

APA, Harvard, Vancouver, ISO, and other styles

Feuer, Alan, Stefan Savev, and Javed A. Aslam. "Implementing and evaluating phrasal query suggestions for proximity search." Information Systems 34, no. 8 (2009): 711–23. http://dx.doi.org/10.1016/j.is.2009.03.012.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Zhang, Xiaojuan, Xixi Jiang, and Jiewen Qin. "Time-aware query suggestion diversification for temporally ambiguous queries." Electronic Library 38, no. 4 (2020): 725–44. http://dx.doi.org/10.1108/el-12-2019-0296.

Full text

Abstract:

Purpose The purpose of this study is to generate diversified results for temporally ambiguous queries and the candidate queries are ensured to have a high coverage of subtopics, which are derived from different temporal periods. Design/methodology/approach Two novel time-aware query suggestion diversification models are developed by integrating semantics and temporality information involved in queries into two state-of-the-art explicit diversification algorithms (i.e. IA-select and xQuaD), respectively, and then specifying the components on which these two models rely on. Most importantly, first explored is how to explicitly determine query subtopics for each unique query from the query log or clicked documents and then modeling the subtopics into query suggestion diversification. The discussion on how to mine temporal intent behind a query from query log is also followed. Finally, to verify the effectiveness of the proposal, experiments on a real-world query log are conducted. Findings Preliminary experiments demonstrate that the proposed method can significantly outperform the existing state-of-the-art methods in terms of producing the candidate query suggestion for temporally ambiguous queries. Originality/value This study reports the first attempt to generate query suggestions indicating diverse interested time points to the temporally ambiguous (input) queries. The research will be useful in enhancing users’ search experience through helping them to formulate accurate queries for their search tasks. In addition, the approaches investigated in the paper are general enough to be used in many domains; that is, experimental information retrieval systems, Web search engines, document archives and digital libraries.

APA, Harvard, Vancouver, ISO, and other styles

Mustar, Agnès, Sylvain Lamprier, and Benjamin Piwowarski. "On the Study of Transformers for Query Suggestion." ACM Transactions on Information Systems 40, no. 1 (2022): 1–27. http://dx.doi.org/10.1145/3470562.

Full text

Abstract:

When conducting a search task, users may find it difficult to articulate their need, even more so when the task is complex. To help them complete their search, search engine usually provide query suggestions. A good query suggestion system requires to model user behavior during the search session. In this article, we study multiple Transformer architectures applied to the query suggestion task and compare them with recurrent neural network (RNN)-based models. We experiment Transformer models with different tokenizers, with different Encoders (large pretrained models or fully trained ones), and with two kinds of architectures (flat or hierarchic). We study the performance and the behaviors of these various models, and observe that Transformer-based models outperform RNN-based ones. We show that while the hierarchical architectures exhibit very good performances for query suggestion, the flat models are more suitable for complex and long search tasks. Finally, we investigate the flat models behavior and demonstrate that they indeed learn to recover the hierarchy of a search session.

APA, Harvard, Vancouver, ISO, and other styles

Pera, Maria Soledad, and Yiu-Kai Ng. "Using online data sources to make query suggestions for children." Web Intelligence 15, no. 4 (2017): 303–23. http://dx.doi.org/10.3233/web-170367.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Santos, Rodrygo L. T., Craig Macdonald, and Iadh Ounis. "Learning to rank query suggestions for adhoc and diversity search." Information Retrieval 16, no. 4 (2012): 429–51. http://dx.doi.org/10.1007/s10791-012-9211-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Rossiello, Gaetano, Annalina Caputo, Pierpaolo Basile, and Giovanni Semeraro. "Modeling concepts and their relationships for corpus-based query auto-completion." Open Computer Science 9, no. 1 (2019): 212–25. http://dx.doi.org/10.1515/comp-2019-0015.

Full text

Abstract:

AbstractQuery auto-completion helps users to formulate their information needs by providing suggestion lists at every typed key. This task is commonly addressed by exploiting query logs and the approaches proposed in the literature fit well in web scale scenarios, where usually huge amounts of past user queries can be analyzed to provide reliable suggestions. However, when query logs are not available, e.g. in enterprise or desktop search engines, these methods are not applicable at all. To face these challenging scenarios, we present a novel corpus-based approach which exploits the textual content of an indexed document collection in order to dynamically generate query completions. Our method extracts informative text fragments from the corpus and it combines them using a probabilistic graphical model in order to capture the relationships between the extracted concepts. Using this approach, it is possible to automatically complete partial queries with significant suggestions related to the keywords already entered by the user without requiring the analysis of the past queries. We evaluate our system through a user study on two different real-world document collections. The experiments show that our method is able to provide meaningful completions outperforming the state-of-the art approach.

APA, Harvard, Vancouver, ISO, and other styles

Ungrangsi, Rachanee, Chutiporn Anutariya, and Vilas Wuwongse. "Enhancing Folksonomy-Based Content Retrieval with Semantic Web Technology." International Journal on Semantic Web and Information Systems 6, no. 1 (2010): 19–38. http://dx.doi.org/10.4018/jswis.2010010102.

Full text

Abstract:

While Flickr, a widely-known photo sharing system, allows users to describe their own photos with tags (aka. folksonomy tags) for indexing purposes, its tag-based photo retrieval function is severely hampered by the inherent nature of folksonomy tags. This paper presents SemFlickr, an application which enhances the search in Flickr with its semantic query suggestion feature. SemFlickr employs SQORE, an ontology retrieval system, to retrieve relevant ontologies from the Semantic Web and then derives query term suggestions from those ontologies. To ensure that the highly related photos will appear at the top of the results, SemFlickr takes the ontological relations among the given query terms to assign tag scores and then generates its ranked results. Experimental outcomes are encouraging and reveal a number of useful insights for developing applications that integrate the Semantic Web and Web 2.0 together.

APA, Harvard, Vancouver, ISO, and other styles

Wang, Hao, Shuyan Wei, Bo-sin Tang, Junhua Chen, and Wenbin Li. "A comparative study on registration system of real estate between Hong Kong and Mainland China." Property Management 36, no. 1 (2018): 5–19. http://dx.doi.org/10.1108/pm-08-2016-0044.

Full text

Abstract:

Purpose The purpose of this paper is to review land/real estate registration practice in Hong Kong, and make an in-depth comparison with Mainland China and finally provide helpful suggestions for the government. Design/methodology/approach Research methods including document analysis/review and comparative study are used in this paper. Findings The main findings focus on the problems existing in the mainland, including narrow query subject, single way of query, limited query time, and lacking of incentive mechanism. Helpful suggestions for real estate registration system in Mainland China are offered based on the comparative study. Practical implications The unified registration system can improve the efficiency of administrative institutions to ensure an open and transparent environment of property right registration, which helps prevent the relevant departments from abusing administrative power and harming the interests of obligees. The findings of this research can serve as a useful reference for policy makers to improve the unified registration system in China. Originality/value The registration system/mechanism determines the efficiency and effectiveness of real estate/land market. However, land registration and query in some countries such as Mainland China have institutional problems which hinder the sustained and healthy development of the real estate industry. The value of this paper is to propose constructive suggestions for such countries/regions by comparing and learning from a good model.

APA, Harvard, Vancouver, ISO, and other styles

Sujini, P., and D. N. Vasundhara. "Implementation of Dynamic Keyword Query Suggestions on Geo Location using Document Proximity." International Journal of Computer Sciences and Engineering 6, no. 7 (2018): 1338–42. http://dx.doi.org/10.26438/ijcse/v6i7.13381342.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Bădărînză, Ioan. "Analyzing the Usefulness of the User’s Browser History for Generating Query Suggestions." Studia Universitatis Babeș-Bolyai Informatica 62, no. 2 (2017): 57–68. http://dx.doi.org/10.24193/subbi.2017.2.05.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Chen, Jinbo, Uwe Scholz, Ruonan Zhou, and Matthias Lange. "LAILAPS-QSM: A RESTful API and JAVA library for semantic query suggestions." PLOS Computational Biology 14, no. 3 (2018): e1006058. http://dx.doi.org/10.1371/journal.pcbi.1006058.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Domingues, Marcos Aurélio, Lucas Rocha, Edleno Silva De Moura, and Altigran Soares Da Silva. "Learning to Rank for Query Auto-completion in the Legal Domain." Journal of the Brazilian Computer Society 31, no. 1 (2025): 382–400. https://doi.org/10.5753/jbcs.2025.4279.

Full text

Abstract:

Most modern Web search engines implement query auto-completion (QAC) to facilitate faster user query input by predicting users' intended query. This is the case of Jusbrasil, Brazil’s most prominent and widely used legal search engine platform. Query auto-completion is typically performed in two steps: matching and ranking. Matching refers to the selection of candidate query from a suggestions dataset. Ranking sorts the matching results according to a score function that attempts to select the top most relevant suggestions for the user. In this paper, our main goal is to explore the effectiveness of learning to rank algorithms on the ranking step for query auto-completion in the legal domain. In particular, we explore four learning to rank algorithms: LambdaMART, XGBoost, RankSVM and Genetic Programming. LambdaMART is widely used in query auto-completion. On the other hand, as far as we know, this is the first time that the RankSVM and XGBoost are used for this task. Additionally, we propose the use of Genetic Programming as a lightweight and viable alternative for query auto-completion. One difficulty for exploring learning to rank algorithms in query auto-completion is the lack of fine-grained training and test datasets, since learning to rank algorithms rely on a large number of features. To bridge this gap, and also to foster research on this area, we propose two datasets with different types of features for query auto-completion in the legal domain. The datasets were created by collecting data from several data sources from Jusbrasil, including contextual features from search query logs, enriched with additional features extracted from other data sources like auto-completion log, document content and metadata available at Jusbrasil. Then, we show that learning to rank is effective for query auto-completion in the legal domain by answering four main research questions: 1) How each feature, specially the novel ones proposed in our work, impact the rankings in query auto-completion?; 2) How effective is learning to rank with respect to the Most Popular Completion (MPC), a ranking algorithm widely adopted as baseline in the literature?; 3) Among the four alternatives experimented, which learning to rank algorithm is more effective in the legal domain?; and 4) How effective is learning to rank with respect to ranking models based on BERT and ColBERT? Finally, we conduct an online A/B test at Jusbrasil.

APA, Harvard, Vancouver, ISO, and other styles

Buza, Antal. "Extension of CQL over Dynamic Databases." JUCS - Journal of Universal Computer Science 12, no. (9) (2006): 1165–76. https://doi.org/10.3217/jucs-012-09-1165.

Full text

Abstract:

CQL, Continuous Query Language is suitable for data stream queries. Sometimes it is better if the queries operate on relational databases and data streams simultaneously. The execution of a CQL query takes a long time (several hours, days or even more). It is not clear what kind of semantics is suitable for the user when the database is updated during the execution of a CQL query. In this paper we give a short description of CQL, a characterization of update-problems, and we offer possible suggestions for the semantic extension of CQL. After the expansion, the CQL would be suitable for solving much more practical problems. The parallel usage of continuous data streams and updatable databases would be settled.

APA, Harvard, Vancouver, ISO, and other styles

Vuong, Tung, Salvatore Andolina, Giulio Jacucci, and Tuukka Ruotsalo. "Spoken Conversational Context Improves Query Auto-completion in Web Search." ACM Transactions on Information Systems 39, no. 3 (2021): 1–32. http://dx.doi.org/10.1145/3447875.

Full text

Abstract:

Web searches often originate from conversations in which people engage before they perform a search. Therefore, conversations can be a valuable source of context with which to support the search process. We investigate whether spoken input from conversations can be used as a context to improve query auto-completion. We model the temporal dynamics of the spoken conversational context preceding queries and use these models to re-rank the query auto-completion suggestions. Data were collected from a controlled experiment and comprised conversations among 12 participant pairs conversing about movies or traveling. Search query logs during the conversations were recorded and temporally associated with the conversations. We compared the effects of spoken conversational input in four conditions: a control condition without contextualization; an experimental condition with the model using search query logs; an experimental condition with the model using spoken conversational input; and an experimental condition with the model using both search query logs and spoken conversational input. We show the advantage of combining the spoken conversational context with the Web-search context for improved retrieval performance. Our results suggest that spoken conversations provide a rich context for supporting information searches beyond current user-modeling approaches.

APA, Harvard, Vancouver, ISO, and other styles

Gupta, Ankita. "COLLEGE ENQUIRY CHATBOT." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 03 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem29688.

Full text

Abstract:

A chatbot is software that is used to interact between a computer and a human in a natural language, as humans chat. Chatbots engage in conversation with users in place of humans and respond to them. The goal of this report on chatbots was to resemble a human being in the way they interact, trying to make the user think he is chatting with another human being. The chatbot application helps students access university-related information from anywhere with an internet connection. This system reduces the work of college administration providing information to students and reduces the workload on the staff to answer all the students' queries. This project aims to develop a college inquiry chatbot that answers any queries posted by students, like college details, course-related questions, location of the college, fee structure, etc. The College Enquiry Chatbot project is built using deep learning algorithms that analyze user’s queries and understand the users' messages. This system is a web application that returns answers to queries. Any individual can simply query the bot. The answers are appropriate to the user's query. The system allows users to query any college-related activities. The user does not have to personally go to the college for an inquiry. The system analyses the question and then answers it for the user. Through the suggestion box, users can also provide suggestions. The system replies using an effective graphic user interface, which implies that a real person is talking to the user. KEYWORDS: Chat bot, Artificial Intelligence, Enquiry, Response, Query.

APA, Harvard, Vancouver, ISO, and other styles

Shah, Chirag, Jingjing Liu, Roberto González-Ibáñez, and Nicholas Belkin. "Exploration of dynamic query suggestions and dynamic search results for their effects on search behaviors." Proceedings of the American Society for Information Science and Technology 49, no. 1 (2012): 1–10. http://dx.doi.org/10.1002/meet.14504901135.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Teixeira Lopes, Carla, Dagmara Paiva, and Cristina Ribeiro. "Effects of language and terminology of query suggestions on medical accuracy considering different user characteristics." Journal of the Association for Information Science and Technology 68, no. 9 (2017): 2063–75. http://dx.doi.org/10.1002/asi.23874.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Ahmed, Adeeb Jalal, Ahmed Jasim Abdulrahman, and A. Mahawish Amar. "A web content mining application for detecting relevant pages using Jaccard similarity." International Journal of Electrical and Computer Engineering (IJECE) 12, no. 6 (2022): 6461–71. https://doi.org/10.11591/ijece.v12i6.pp6461-6471.

Full text

Abstract:

The tremendous growth in the availability of enormous text data from a variety of sources creates a slew of concerns and obstacles to discovering meaningful information. This advancement of technology in the digital realm has resulted in the dispersion of texts over millions of web sites. Unstructured texts are densely packed with textual information. The discovery of valuable and intriguing relationships in unstructured texts demands more computer processing. So, text mining has developed into an attractive area of study for obtaining organized and useful data. One of the purposes of this research is to discuss text pre-processing of automobile marketing domains in order to create a structured database. Regular expressions were used to extract data from unstructured vehicle advertisements, resulting in a well-organized database. We manually develop unique rule-based ways of extracting structured data from unstructured web pages. As a result of the information retrieved from these advertisements, a systematic search for certain noteworthy qualities is performed. There are numerous approaches for query recommendation, and it is vital to understand which one should be employed. Additionally, this research attempts to determine the optimal value similarity for query suggestions based on user-supplied parameters by comparing MySQL pattern matching and Jaccard similarity.

APA, Harvard, Vancouver, ISO, and other styles

Shahidi, Niloofar, Xuanzhi Lin, Yuda Munarko, Laila Rasmy, and Tram Ngo. "AQUA: an Advanced QUery Architecture for the SPARC Portal." F1000Research 10 (September 16, 2021): 930. http://dx.doi.org/10.12688/f1000research.73018.1.

Full text

Abstract:

The Stimulating Peripheral Activity to Relieve Conditions (SPARC) program integrates biological and neural information to create anatomical and functional maps of the peripheral nervous system. The SPARC Portal hosts a dynamic storage for the datasets, models, and resources to help the researchers find and produce data. Currently, the SPARC Portal provides a primary search tool, which lacks some features to improve the search experience. To purposefully retrieve the required information from the stored datasets and resources, we have developed an Advanced QUery Architecture (AQUA) for the SPARC Portal. Near-real-time auto-completion of the queries, close-matches suggestions, and multiple filters to narrow or sort the results are the major features of AQUA with the goal to enhance the usability of the SPARC search engine. AQUA is available from: https://github.com/SPARC-FAIR-Codeathon/aqua

APA, Harvard, Vancouver, ISO, and other styles

Shefali, Singhal, and Tanwar Poonam. "A prediction model for benefitting e-commerce through usage of regional data: A new framework." International Journal of Artificial Intelligence (IJ-AI) 10, no. 4 (2021): 1009–18. https://doi.org/10.11591/ijai.v10.i4.pp1009-1018.

Full text

Abstract:

Today during ‘Covid-20’, people are more inclined towards online shopping. In general practice, analysis of browsing history and customer’s micro behaviour against online shopping habits have been used for future suggestions. Due to this, the predictions made were suffereing from oversimilarity problem and the user was unable to find any novelty in the recommended items. Observing these issues, e-shopping quality can be enhanced by adding a factor other than similarity. The current research suggests and advertise those products which belongs to a person’s region. For this research work the data has been collected on the basis of area-wise, like, country-based seggregation. Here the considered dataset belongs to country, ‘India’, its culture, its handicraft and its citizens. Datasets and their combinations based on multiple attributes are input for the proposed predictive system. In this paper, existing data is also considered for collecting customers demographic details which is further mapped with the area-wise dataset. Also, a framework has been proposed which uses database and user query as input for its predictive system in order to generate default suggestions for the user other than the submitted query also.

APA, Harvard, Vancouver, ISO, and other styles

Ren Jie, Yao Shuai, and Cheng Wanhui. "RESEARCH ON THE MEASUREMENT OF MARKETING POST COMPETENCY IN THE FAST FASHION CLOTHING INDUSTRY." Malaysian Journal of Business and Economics (MJBE) 10, no. 1 (2023): 58–70. http://dx.doi.org/10.51200/mjbe.v10i1.4176.

Full text

Abstract:

With the renewal of traditional industries and the emergence of modern industries, new requirements are put forward for the competence of marketing talents in the fast fashion industry. Starting from the competency of talent matching in the fast fashion clothing industry, this paper according to the characteristics of marketing pos first query to query marketing job requirements, the interview method, and the data survey method to measure the competency dimensions of different marketing posts. We collected 453 samples from enterprises and used SPSS 22.0 for data analysis to explore the fast fashion industry. The proposed competency elements of marketing talents mainly include knowledge and skills, personal characteristics, internal ability, and self-awareness. Finally, we proposed reasonable suggestions for post-machining China on marketing talents in the fast fashion clothing industry.

APA, Harvard, Vancouver, ISO, and other styles

Bordogna, Gloria, Alessandro Campi, Giuseppe Psaila, and Stefania Ronchi. "Disambiguated query suggestions and personalized content-similarity and novelty ranking of clustered results to optimize web searches." Information Processing & Management 48, no. 3 (2012): 419–37. http://dx.doi.org/10.1016/j.ipm.2011.03.008.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Singhal, Shefali, and Poonam Tanwar. "A prediction model for benefitting e-commerce through usage of regional data: A new framework." IAES International Journal of Artificial Intelligence (IJ-AI) 10, no. 4 (2021): 1009. http://dx.doi.org/10.11591/ijai.v10.i4.pp1009-1018.

Full text

Abstract:

Today during ‘Covid-20’, people are more inclined towards online shopping. In general practice, analysis of browsing history and customer’s micro behaviour against online shopping habits have been used for future suggestions. Due to this, the predictions made were suffereing from over-similarity problem and the user was unable to find any novelty in the recommended items. Observing these issues, e-shopping quality can be enhanced by adding a factor other than similarity. The current research suggests and advertise those products which belongs to a person’s region. For this research work the data has been collected on the basis of area-wise, like, country-based seggregation. Here the considered dataset belongs to country, ‘India’, its culture, its handicraft and its citizens. Datasets and their combinations based on multiple attributes are input for the proposed predictive system. In this paper, existing data is also considered for collecting customers demographic details which is further mapped with the area-wise dataset. Also, a framework has been proposed which uses database and user query as input for its predictive system in order to generate default suggestions for the user other than the submitted query also.

APA, Harvard, Vancouver, ISO, and other styles

Alahmari, Fahad, James A. Thom, and Liam Magee. "A model for ranking entity attributes using DBpedia." Aslib Journal of Information Management 66, no. 5 (2014): 473–93. http://dx.doi.org/10.1108/ajim-12-2013-0148.

Full text

Abstract:

Purpose – Previous work highlights two key challenges in searching for information about individual entities (such as persons, places and organisations) over semantic data: query ambiguity and redundant attributes. The purpose of this paper is to consider these challenges and proposes the Attribute Importance Model (AIM) for clustering and ranking aggregated entity search to improve the overall users’ experience of finding and navigating entities over the Web of Data. Design/methodology/approach – The proposed model describes three distinct techniques for augmenting semantic search: first, presenting entity type-based query suggestions; second, clustering aggregated attributes; and third, ranking attributes based on their importance to a given query. To evaluate the model, 36 subjects were recruited to experience entity search with and without AIM. Findings – The experimental results show that the model achieves significant improvements over the default method of semantic aggregated search provided by Sig.ma, a leading entity search and navigation tool. Originality/value – This proposal develops more informative views for aggregated entity search and exploration to enhance users’ understanding of semantic data. The user study is the first to evaluate user interaction with Sig.ma's search capabilities in a systematic way.

APA, Harvard, Vancouver, ISO, and other styles

Rehman Khan, Haseeb ur, Chen Kim Lim, and Shir Li Wang. "Contextual Suggestion and Recommendation Systems: A Review on Challenges in User Modeling and Privacy Concern." Journal of ICT in Education 8, no. 1 (2021): 43–60. http://dx.doi.org/10.37134/jictie.vol8.1.4.2021.

Full text

Abstract:

The contextual suggestion systems are emerging as modified recommendation systems integrated with information retrieval techniques to search within large databases with the purpose to provide a user with a list of suggestions based on context i.e. location, time of the day, any day of the week (weekdays or weekend). The goal of this research is to conduct a systematic review in the field of contextual suggestion and recommendation systems incorporate with smart cities as the repositories of large datasets. This paper highlights the concerns linked with approaches being used in the contextual suggestion system and discussing various approaches which are being utilized in the contextual suggestion system. The keywords for query searching include; “contextual suggestion”, “recommendation system” and “smart city” which identified 191 papers published from 2012 to 2020. Four major article repositories were considered for searching (i) Science Direct, (ii) Scopus, (iii) IEEE, and (iv) Web of Science. The review was conducted under the protocols of four phases (i) Query searching in major article’s repositories, (ii) remove duplicates, (iii) scan title and abstract, and (iv) complete article reading. To identify the gaps in ongoing research a taxonomy analysis was exemplified into categories which further divided into subcategories, the main categories are highlighted as (i) review articles, (ii) model/framework and, (iii) smart city and applications. The critical analysis highlighted the limitations of approaches being used in the field and discussed the challenges. The review also reveals that most researches utilized approaches based on content-based filtering, collaborative filtering, preference-based product ranking, language modelling, evaluation measures were precision, normalized discounted cumulative, mean reciprocal rank, and the test collection comprised of internet resources.

APA, Harvard, Vancouver, ISO, and other styles

Rehman Khan, Haseeb Ur, Chen Kim Lim, Minhaz Farid Ahmed, Kian Lam Tan, and Mazlin Bin Mokhtar. "Systematic Review of Contextual Suggestion and Recommendation Systems for Sustainable e-Tourism." Sustainability 13, no. 15 (2021): 8141. http://dx.doi.org/10.3390/su13158141.

Full text

Abstract:

Agenda 2030 of Sustainable Development Goals (SDGs) 9 and 11 recognizes tourism as one of the central industries to global development to tackle global challenges. With the transformation of information and communication technologies (ICT), e-tourism has evolved globally to establish commercial relationships using the Internet for offering tourism-related products, including giving personalised suggestions. The contextual suggestion has emerged as a modified recommendation system that is integrated with information-retrieval techniques within large databases to provide tourists with a list of suggestions based on contexts, such as location, time of day, or day of the week (weekdays or weekends). This study surveyed literature in the field of contextual suggestion and recommendation systems with a focus on e-tourism. The concerns linked with approaches used in contextual suggestion and recommendation systems are highlighted in this systematic review, while motivations, recommendations, and practical implications in e-tourism are also discussed in this paper. A query search using the keywords “contextual suggestion system”, “recommendation system”, and “tourism” identified 143 relevant articles published from 2012 to 2020. Four major repositories are considered for searching, namely, (i) Science Direct, (ii) Scopus, (iii) IEEE, and (iv) Web of Science. This review was carried out under the protocols of four phases, namely, (i) query searching in major article repositories, (ii) removal of duplicates, (iii) scan of title and abstract, and (iv) complete reading of articles. To identify the gaps in current research, a taxonomy analysis was exemplified into categories and subcategories. The main categories were highlighted as (i) review articles, (ii) model/framework, and (iii) applications. Critical analysis was carried out on the basis of the available literature on the limitations of approaches used in contextual suggestion and recommendation systems. In conclusion, the approaches used are mainly based on content-based filtering, collaborative filtering, preference-based product ranking, and language modelling. The evaluation measures for the contextual suggestion system include precision, normalized discounted cumulative, and mean reciprocal rank, while test collections comprise Internet resources. Given that the tourism industry contributed to the environmental and social-economic development, contextual suggestion and recommendation systems have presented themselves to be relevant in integrating and achieving SDG 9 and SDG 11 in many ways such as web-based e-services by the government sector and smart gadgets based on reliable and real-time data and information for city planners as well as law enforcement personnel in a sustainable city.

APA, Harvard, Vancouver, ISO, and other styles

SIJIN, P. "INTENT-BASED DIVERSIFICATION FOR FUZZY KEYWORD SEARCH OVER XML DATA." IJIERT - International Journal of Innovations in Engineering Research and Technology 5, no. 3 (2018): 57–63. https://doi.org/10.5281/zenodo.1454093.

Full text

Abstract:

The keyword queries over various data forms have wide attention nowadays. The query intention can easily be obtained by comparing the keyword with some query suggestions. An annotation process can be recommended to generate the structured meta - data for a document. In the proposed system the conceptualization and measure of co - occurrence count of a typed term has considered on the basis of semantic relatedness and similarity between terms . This should be useful for the retrieval of information by search query with short and vague keywords. Apart fro m this,using a fuzzy uncertainty function the fuzzy semantic of a query can be easily obtained. This will reveal the uncertainties among the co - occurring terms. The closest matching terms can be easily constructed by using the keyword similarity semantics . The edit distance and gram based pattern matching methods are used to check the closeness of keyword similarity of terms . The concept based clustering is used to hold the data in a multidimensional space. The proposed dimension reduction method reduces the cardinality of the result set in the direction of Eigen vectors calculated for the selected features. The outliers of t he concept vector can set to the required level on the basis of concept density. The attributes and related features are store d as metadata information in XML files for more precise representation. https://www.ijiert.org/paper-details?paper_id=141155

APA, Harvard, Vancouver, ISO, and other styles

Wu, Linfeng, and Peng Liu. "Investigation on the Regional Distribution of the Development of Chinese Social Organization Standards and the Promotion of Quality Improvement in Related Industries." Mathematical Problems in Engineering 2023 (January 10, 2023): 1–16. http://dx.doi.org/10.1155/2023/8772161.

Full text

Abstract:

Based on the query data of the national social organization standard information platform, the registration of Chinese social organizations on the national social organization standard information platform and the publication of social organization standards in recent six years are counted, and the correlation is compared with the population of provinces and cities in China, the innovation ability index, GDP, and the national invention patents. The experience of social organization standardization management in the United States and Germany is briefly analyzed. This paper discusses the current situation of the development of Chinese social organization standards and the problems existing in the development process and puts forward suggestions on the management of social organization standardization, in order to provide management suggestions for the high-quality development of China’s industry.

APA, Harvard, Vancouver, ISO, and other styles

Moosavinasab, Soheil, Emre Sezgin, Huan Sun, Jeffrey Hoffman, Yungui Huang, and Simon Lin. "DeepSuggest: Using Neural Networks to Suggest Related Keywords for a Comprehensive Search of Clinical Notes." ACI Open 05, no. 01 (2021): e1-e12. http://dx.doi.org/10.1055/s-0041-1729982.

Full text

Abstract:

Abstract Objective A large amount of clinical data are stored in clinical notes that frequently contain spelling variations, typos, local practice-generated acronyms, synonyms, and informal words. Instead of relying on established but infrequently updated ontologies with keywords limited to formal language, we developed an artificial intelligence (AI) assistant (named “DeepSuggest”) that interactively offers suggestions to expand or pivot queries to help overcome these challenges. Methods We applied an unsupervised neural network (Word2Vec) to the clinical notes to build keyword contextual similarity matrix. With a user's input query, DeepSuggest generates a list of relevant keywords, including word variations (e.g., formal or informal forms, synonyms, abbreviations, and misspellings) and other relevant words (e.g., related diagnosis, medications, and procedures). Human intelligence is then used to further refine or pivot their query. Results DeepSuggest learns the semantic and linguistic relationships between the words from a large collection of local notes. Although DeepSuggest is only able to recall 0.54 of Systematized Nomenclature of Medicine (SNOMED) synonyms on average among the top 60 suggested terms, it covers the semantic relationship in our corpus for a larger number of raw concepts (6.3 million) than SNOMED ontology (24,921) and is able to retrieve terms that are not stored in existing ontologies. The precision for the top 60 suggested words averages at 0.72. Usability test resulted that DeepSuggest is able to achieve almost twice the recall on clinical notes compared with Epic (average of 5.6 notes retrieved by DeepSuggest compared with 2.6 by Epic). Conclusion DeepSuggest showed the ability to improve retrieval of relevant clinical notes when implemented on a local corpus by suggesting spelling variations, acronyms, and semantically related words. It is a promising tool in helping users to achieve a higher recall rate for clinical note searches and thus boosting productivity in clinical practice and research. DeepSuggest can supplement established ontologies for query expansion.

APA, Harvard, Vancouver, ISO, and other styles

Younas, Rabia, Hafiz Burhan Ul Haq, and Muhammad Daniyal Baig. "A Framework for Extensive Content-Based Image Retrieval System Incorporating Relevance Feedback and Query Suggestion." Spectrum of Operational Research 1, no. 1 (2024): 13–32. http://dx.doi.org/10.31181/sor1120242.

Full text

Abstract:

Over the last decade, there is a huge amount of images in which visual information has become increasingly important. If the images are to be utilized, they must be organized into databases, from there it can be searched based on different criteria. Content-based Image retrieval (CBIR) frameworks have turned into a mainstream subject of exploration; for their ability to retrieve images based on the real visual content rather than by manually connected textual descriptions. In the CBIR framework, analysis and interpretation of image information in large and diverse image databases is evidently complex because there is no prior information on the size or scale of individual structures within the images to be analyzed. In CBIR, retrieval is based on visual image features, which can be extracted automatically from the images with the help of human intervention, namely a technique called relevance feedback. Nonetheless, an efficient way of differentiating the visual content of images is complex to produce. Therefore, rather than a perfect solution CBIR systems must be able to exploit a partial solution to the problem of image understanding. In this paper, there is implementation of a CBIR framework is introduced that not only tries to efficiently capture the user intent based on the feedback but also provide query suggestions that can help its users to pose better queries in order to retrieve desired results in an efficient manner. The proposed technique is straightforward to implement and scopes efficiently to huge datasets. Extensive experiments on diverse real datasets with image similarity measures have revealed the dominance of the proposed method over original algorithms.

APA, Harvard, Vancouver, ISO, and other styles

Amin, Ruhul, Taufik Djatna, Annisa Annisa, and Imas Sukaesih Sitanggang. "SKYLINE QUERY BASED ON USER PREFERENCES IN CELLULAR ENVIRONMENTS." JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) 9, no. 1 (2023): 143–53. http://dx.doi.org/10.33480/jitk.v9i1.4192.

Full text

Abstract:

The recommendation system is an important tool for providing personalized suggestions to users about products or services. However, previous research on individual recommendation systems using skyline queries has not considered the dynamic personal preferences of users. Therefore, this study aims to develop an individual recommendation model based on the current individual preferences and user location in a mobile environment. We propose an RFM (Recency, Frequency, Monetary) score-based algorithm to predict the current individual preferences of users. This research utilizes the skyline query method to recommend local cuisine that aligns with the individual preferences of users. The attributes used in selecting suitable local cuisine include individual preferences, price, and distance between the user and the local cuisine seller. The proposed algorithm has been implemented in the JALITA mobile-based Indonesian local cuisine recommendation system. The results effectively recommend local cuisine that matches the dynamic individual preferences and location of users. Based on the implementation results, individual recommendations are provided to mobile users anytime and anywhere they are located. In this study, three skyline objects are generated: soto betawi (C5), Mie Aceh Daging Goreng (C4), and Gado-gado betawi (C3), which are recommended local cuisine based on the current individual preferences (U1) and user location (L1). The implementation results are exemplified for one user located at (U1L1), providing recommendations for soto betawi (C5) with an individual preference score of 0.96, Mie Aceh Daging Goreng (C4) with an individual preference score of 0.93, and Gado-gado betawi (C3) with an individual preference score of 0.98. Thus, this research contributes to the field of individual recommendation systems by considering the dynamic user location and preferences.

APA, Harvard, Vancouver, ISO, and other styles

Malik, Sushma, Anamika Rana, and Mamta Bansal. "A Survey of Recommendation Systems." Information Resources Management Journal 33, no. 4 (2020): 53–73. http://dx.doi.org/10.4018/irmj.2020100104.

Full text

Abstract:

Today's internet is able to discover almost any product or piece of information. The large amounts of unfiltered information returned by an internet query calls for filters able to validate and rank the available options. Recommender systems (RSs) are a software tool designed to qualify the options available and make suggestions that align with the user's requirements and expectations. This paper reviews some significant applications of RSS in various areas like videos, music, eCommerce sites, news, and many more. It also reviews various filtering techniques like collaborative, content based, and hybrid.

APA, Harvard, Vancouver, ISO, and other styles

Angira, Patel*1 &., and JyotindraDharwa2 Dr. "GRAPH-BASED RECOMMENDATION MODEL ENVISIONED FOR VARIOUS DOMAINS." GLOBAL JOURNAL OF ENGINEERING SCIENCE AND RESEARCHES 4, no. 12 (2017): 38–45. https://doi.org/10.5281/zenodo.1115385.

Full text

Abstract:

Recommender systems are envisioned and design to serve automatic recommendations for various services and products to active consumer. Such systems can find similar items and sort to generate top N suggestions as per users past transaction, location, knowledge, profiles, preferences or choices of otherpeople. This research illustrates potential use of graph-based model intended for recommendation system and designed for various domains. The ultramodern graph technology and state-of-the-art graph query tool is prime motivation behind this research work. The implementation has been carried out with profound online graph management tool known as ‘neo4j’ and recommendation algorithm has been executed with graph query language called ‘Cypher’. The experiment and evaluation shows success of proposed model for increasing efficiency of the system which is emerging need of the present. The outcome of this research has great potential which can be put into practice and it can offer course of action for advance technical revolution in forthcoming era of Big data. This research also encourages anyone who wants to implement graph-based model for recommendation system.  

APA, Harvard, Vancouver, ISO, and other styles

Researcher. "INTELLIGENT COLLEGE ENQUIRY CHATBOT USING NLP FOR ENHANCED STUDENT INTERACTION." Journal of Advanced Research Engineering and Technology (JARET) 3, no. 2 (2024): 30–37. https://doi.org/10.5281/zenodo.14204416.

Full text

Abstract:

This project aims to develop a College Enquiry Chatbot that leverages Natural Language Processing (NLP) techniques to address queries posted by students, such as college details, course-related questions, location, fee structure, and more. The chatbot is a web application designed to analyze and comprehend user messages using machine learning algorithms integrated with NLP for enhanced query understanding and response accuracy. Users can interact with the system by simply typing their queries into the chatbot, which provides precise and contextually relevant answers. The chatbot eliminates the need for students to visit the college in person for inquiries. Additionally, users can provide feedback or suggestions through a dedicated suggestion box. The system features an engaging Graphical User Interface (GUI), simulating an interaction akin to conversing with a real person. The project employs HTML, CSS, and JavaScript for the frontend and Python for the backend, with NLP models enabling robust question analysis and response generation.

APA, Harvard, Vancouver, ISO, and other styles

Köhler, Juliane. "Seeking Employment in a Non-Native Language." International Journal of Information, Diversity, & Inclusion (IJIDI) 4, no. 2 (2020): 108–15. http://dx.doi.org/10.33137/ijidi.v4i2.33144.

Full text

Abstract:

In 2015, over a million refugees arrived in Germany. After settling into their new environments, these refugees needed to find employment. The search for work, and the orientation to the German job market, increasingly takes place on the Internet requiring language skills and digital competence. The purpose of this study is to examine the online information seeking strategies of refugees in Germany and barriers that affect a successful search. The study builds on data collected from an online study with seven refugees solving different tasks. Search queries for each participant were recorded and analyzed using an approach of both the mixed and grounded theory method. Participants did not follow any observable systematic strategy but relied on supporting tools such as the search engine for providing suggestions or corrections and translation websites. Participants mainly used three formulation tactics: copying, suggestions, and autonomous formulating. The formulation of the query seemed to be the most challenging to the participants.

APA, Harvard, Vancouver, ISO, and other styles

Ying, Jieqiong, and Gang Hong. "A Cross-cultural Comparative Study of Requests Made in Chinese by South Korean and French Learners." Journal of Language Teaching and Research 11, no. 1 (2020): 54. http://dx.doi.org/10.17507/jltr.1101.07.

Full text

Abstract:

This study aims to examine the differences of pragmatic strategies of requests made in Chinese by South Korean and French learners, in comparison to those made by Chinese native speakers (CNS). Using a Discourse Completion Test (DCT) questionnaire as the research tool, 20 Chinese, 20 French students and 20 South Korean students from the Shanghai International Studies University (SISU) were randomly selected to complete the questionnaire. The response data from the Chinese student questionnaires were used as the baseline data for comparison as well as generating a modified coding scheme. The results show that Chinese speakers and South Korean learners tend to be more direct by using “query preparatory” and “mood derivable” as head acts, while French learners tend to be indirect by primarily using “query preparatory.” In terms of sociopragmatics, the results show that Korean learners and Chinese tend to be hierarchical and collectivistic, while French students are prone to be egalitarian and individualistic. L2 transfer, inductive/deductive mindset, unfamiliarity, and varied perceptions of politeness could be possible reasons for the differences in request strategies. This study concludes with suggestions for future research and pedagogy.

APA, Harvard, Vancouver, ISO, and other styles

Zhang, Shaoqing, Zhuosheng Zhang, Kehai Chen, et al. "Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 24 (2025): 25904–12. https://doi.org/10.1609/aaai.v39i24.34784.

Full text

Abstract:

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to real-world applications. Existing work faces challenges in both training efficiency and generalization capabilities (i.e., Reinforcement Learning from Human Feedback and Red-Teaming). Developing effective strategies to enable LLMs to resist continuously evolving jailbreak attempts represents a significant challenge. To address this challenge, we propose a novel defensive paradigm called GuidelineLLM, which assists LLMs in recognizing queries that may have harmful content. Before LLMs respond to a query, GuidelineLLM first identifies potential risks associated with the query, summarizes these risks into guideline suggestions, and then feeds these guidelines to the responding LLMs. Importantly, our approach eliminates the necessity for additional safety fine-tuning of the LLMs themselves; only the GuidelineLLM requires fine-tuning. This characteristic enhances the general applicability of GuidelineLLM across various LLMs. Experimental results demonstrate that GuidelineLLM can significantly reduce the attack success rate (ASR) against LLM (an average reduction of 34.17% ASR) while maintaining the usefulness of LLM in handling benign queries.

APA, Harvard, Vancouver, ISO, and other styles

VARGES, S., F. WENG, and H. PON-BARRY. "Interactive question answering and constraint relaxation in spoken dialogue systems." Natural Language Engineering 15, no. 1 (2009): 9–30. http://dx.doi.org/10.1017/s1351324908004889.

Full text

Abstract:

AbstractWe explore the relationship between question answering and constraint relaxation in spoken dialogue systems and develop dialogue strategies for selecting and presenting information succinctly. In particular, we describe methods for dealing with the results of database queries in information-seeking dialogues. Our goal is to structure the dialogue in such a way that the user is neither overwhelmed with information nor left uncertain as to how to refine the query further. We present two sets of evaluation results for a restaurant selection task: one is a system performance evaluation experiment involving twenty subjects, the other is an experimental evaluation of the use of suggestions involving sixteen subjects.

APA, Harvard, Vancouver, ISO, and other styles

Peng, Shuaiqiang. "Archives Management in the Information Age: Practical Exploration of Computer Technology Integration." Journal of Computing and Electronic Information Management 17, no. 1 (2025): 21–24. https://doi.org/10.54097/zesdk459.

Full text

Abstract:

With the advent of the information age, the explosive growth of information has brought great opportunities and challenges to hospitals. It is a very difficult problem to solve the problems of huge information and small storage capacity of paper files, huge space required and slow data query in traditional file management. How to screen out the data suitable for hospital development through huge information to support the suggestions and improve work efficiency is a very important role of archives management in the new era. This paper will discuss the application of file management in hospital and analyze its actual effect, so as to provide data support for related work.

APA, Harvard, Vancouver, ISO, and other styles

Nabila, Aisyatun, and Hafid Syaifullah. "Analisis Sistem Antrian Proses Muat Pakan Ternak Menggunakan Metode Multiple Channel Query System (M/M/S) di PT. JKL." Industrika : Jurnal Ilmiah Teknik Industri 9, no. 2 (2025): 327–36. https://doi.org/10.37090/indstrk.v9i2.1936.

Full text

Abstract:

The purpose of this research is to analyze the effectiveness level of the service system in the commercial livestock feed loading process at PT. JKL and to provide improvement suggestions to enhance the performance of the queue system in the livestock feed loading process. The queuing system problem is solved by implementing the queuing theory concept using the multiple channel query system (M/M/S) method. The use of the M/M/S method can analyze the performance of the queuing system in the livestock feed loading process, which provides 6 service servers during the period from 08:30 to 11:30 and 1 queue line. This research uses primary data consisting of the number of vehicle arrivals and the number of vehicles that have been served. From the data processing results, the highest server utilization rate of 40.9% was obtained during the time period between 08:30-09:31 with 3 vehicles in the system. The probability of no vehicles in the system is 8.54% with an average time of vehicles in the system being 5.522 minutes. From these results, suggestions can be made to improve the performance of the queue system by adding forklift operator staff and increasing the loading speed of the contract workers. Keywords: Arrival, Loading Process, Queue, Service

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!