Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 16261 - 16290 of 178284

Full-Text Articles in Entire DC Network

Detection Of Cardiovascular Diseases Using Predictive Models Based On Deep Learning Techniques: A Hybrid Neutrosophic Ahp-Topsis Approach For Model Selection, Julio Barzola-Monteses, Rosangela Caicedo-Quiroz, Franklin Parrales-Bravo, Cristhian Medina-Suarez, Wendy Yanez-Pazmino, David Zabala-Blanco, Maikel Y. Leyva-Vazquez Nov 2024

Detection Of Cardiovascular Diseases Using Predictive Models Based On Deep Learning Techniques: A Hybrid Neutrosophic Ahp-Topsis Approach For Model Selection, Julio Barzola-Monteses, Rosangela Caicedo-Quiroz, Franklin Parrales-Bravo, Cristhian Medina-Suarez, Wendy Yanez-Pazmino, David Zabala-Blanco, Maikel Y. Leyva-Vazquez

Neutrosophic Sets and Systems

In Ecuador and globally, cardiovascular diseases are the leading cause of mortality, accounting for a worrying 26.49% of deaths in 2019. An approach based on deep learning is applied to improve the capacity for early prediction and reduce its incidence. In this work, three different models were proposed and compared: deep neural networks (DNN), convolutional neural networks (CNN), and multilayer perceptron (MLP). Experiments were conducted in two scenarios: one using a dataset that included 12 variables, and another in which the variables were reduced to those most significantly correlated with cardiovascular disease, i.e., 4 variables; both scenarios with 918 clinical …


Creative Exploration Of Yagé In Intrapersonal Discovery Through The Plithogenic Iadov Method, Marcela Ximena Parra Pérez, Arleth M. Márquez Bermeo Nov 2024

Creative Exploration Of Yagé In Intrapersonal Discovery Through The Plithogenic Iadov Method, Marcela Ximena Parra Pérez, Arleth M. Márquez Bermeo

Neutrosophic Sets and Systems

Post-Yage visions, influenced by ancestral Indigenous practices, have had a significant impact on the worldview and collective consciousness of participants. The objective of this study is to analyze post-Yage visions from an intercultural perspective, evaluating cultural depth, creativity, psychological impact, social relevance, and clari-ty in interpretation. The objective is to understand their influence on the Indigenous worldview and their im-pact on individual and collective consciousness through the modeling of the plithogenic IADOV. Correlations were identified between interpretive clarity, creativity, and psychological impact, highlighting their influence on the identity and social awareness of participants. In conclusion, this study provides deeper insights …


Neutrosophic Analysis Of Strategies To Improve Productivity In An Restaurant Chain, Efrén Gonzalo Montenegro Cueva, Milena Alejandra Napa Alcívar Nov 2024

Neutrosophic Analysis Of Strategies To Improve Productivity In An Restaurant Chain, Efrén Gonzalo Montenegro Cueva, Milena Alejandra Napa Alcívar

Neutrosophic Sets and Systems

The study analyzed productivity in an Ecuadorian restaurant chain using a multicriteria approach within a neu-trosophic framework. The research focused on identifying effective strategies to optimize processes and address-ing specific challenges such as staff turnover and compensation management. The TOPSIS method, combined with bipolar neutrosophic numbers, was employed to evaluate a group of strategies based on high-impact crite-ria. The results highlighted the implementation of economic incentives, training and retention programs, and performance management systems as the most effective alternatives. In contrast, internal communication cam-paigns and flexible schedules were found to be less prioritized. The research demonstrated the utility of neutro-sophic …


Applying Neutrosophic Natural Language Processing To Analyze Complex Phenomena In Interdisciplinary Contexts, Diego Fernando Coka Flores, Ignacio Fernando Barcos Arias, María Elena Infante Miranda, Omar Mar Cornelio Nov 2024

Applying Neutrosophic Natural Language Processing To Analyze Complex Phenomena In Interdisciplinary Contexts, Diego Fernando Coka Flores, Ignacio Fernando Barcos Arias, María Elena Infante Miranda, Omar Mar Cornelio

Neutrosophic Sets and Systems

The paper addresses the challenge of integrating natural language processing (NLP) with neutrosophic logic to solve problems where uncertainty, ambiguity, and indeterminacy play a critical role. This approach becomes particularly relevant in an increasingly digitalized world, where human-machine interaction requires a deeper understanding of linguistic and contextual nuances. Despite advances in conventional NLP, many existing methodologies lack tools to effectively manage undefined or contradictory elements present in real data. In this context, neutrosophic logic offers an innovative framework to model and analyze complex and multifaceted human perceptions. The study applies a methodology that combines advanced NLP techniques with neutrosophic analytical …


Application Of The Plithogenic Iadov Approach To Evaluate Satisfaction With The Implementation Of Indigenous Rights, Gıovanna Fernanda Vınueza Arroyo, Tanya Tupamara Camargo Martinez, Manuel Augusto Suarez Albıñol, Joffre R. Paladines Rodriguez Nov 2024

Application Of The Plithogenic Iadov Approach To Evaluate Satisfaction With The Implementation Of Indigenous Rights, Gıovanna Fernanda Vınueza Arroyo, Tanya Tupamara Camargo Martinez, Manuel Augusto Suarez Albıñol, Joffre R. Paladines Rodriguez

Neutrosophic Sets and Systems

The present study addresses a crucial challenge in the evaluation of complex systems: the need to incorporate a holistic view that contemplates not only defined elements but also those that are intrinsically ambiguous or uncertain. The research focuses on the application of the Plithogenic IADOV approach, a model based on neutrosophic logic, to overcome the limitations of traditional methodologies that often fall short when addressing phenomena containing contradictory or unknown dimensions. In the existing literature, despite the wealth of approaches used for the evaluation of systems, there is a perceived lack of methodologies that effectively manage the indeterminacy inherent in …


Use Of Neutrosophic Cognitive Maps For A More Complex Representation Of Human Perceptions, Juan Alberto Rojas Cardenas, Nelson Francisco Freire Sanchez, Alipio Absalon Cadena Pozo, Karina Perez Teruel Nov 2024

Use Of Neutrosophic Cognitive Maps For A More Complex Representation Of Human Perceptions, Juan Alberto Rojas Cardenas, Nelson Francisco Freire Sanchez, Alipio Absalon Cadena Pozo, Karina Perez Teruel

Neutrosophic Sets and Systems

The research addresses a central problem in the modeling and analysis of human perceptions: the need for tools that capture more richly and accurately the complexity inherent in opinions, especially in contexts of high uncertainty and contradiction. In a scenario where traditional methodologies such as conventional cognitive maps lack the flexibility to represent nuances such as ambiguity or non-linear relationships, a key opportunity arises to explore innovative approaches. This methodological gap raises the question of how to integrate neutrosophic logic into analytical tools to improve the representation and analysis of complex perceptions in diverse environments. The study proposes and validates …


Using The Neutrosophic N-Ahp Method To Prioritize Variables And Expert Analysis, Oswaldo Lıber Andrade Salazar, Lenı Cecılıa Campaña Muñoz, Second Huacón Farm, Angel Braulio Martinez Vasquez Nov 2024

Using The Neutrosophic N-Ahp Method To Prioritize Variables And Expert Analysis, Oswaldo Lıber Andrade Salazar, Lenı Cecılıa Campaña Muñoz, Second Huacón Farm, Angel Braulio Martinez Vasquez

Neutrosophic Sets and Systems

The study focuses on addressing a growing challenge in complex decision-making: how to prioritize key variables in an environment of inherent uncertainty and contradiction. In this context, the research explores the implementation of the neutrosophic N-AHP method, a variant of Hierarchical Process Analysis (HPA) that incorporates neutrosophic logic to handle ambiguity and indeterminacy in the evaluation of critical variables. Although traditional HPA has been widely used to prioritize options, it has been limited in contexts where expert perceptions are not clear-cut or are marked by high levels of uncertainty. This work seeks to overcome those limitations, proposing a more flexible …


Analyzing Internal And External Factors For Ecological Preservation In San Juan De Pastocalle: A Combined Swot And Neutrosophic Ahp Approach, Magaly Lucia Benalcázar Luna, Ana Lucía Naranjo, Luis Fernando Muisin Salazar Nov 2024

Analyzing Internal And External Factors For Ecological Preservation In San Juan De Pastocalle: A Combined Swot And Neutrosophic Ahp Approach, Magaly Lucia Benalcázar Luna, Ana Lucía Naranjo, Luis Fernando Muisin Salazar

Neutrosophic Sets and Systems

This study aimed to analyze the role of Community Circles in preserving the ecological link in the rural parish of San Juan de Pastocalle, identifying both the factors that enhance and those that limit this process. The SWOT analysis combined with the neutrosophic AHP method was applied to evaluate the key elements that affect eco-logical sustainability in the community. The results revealed that the main weaknesses were the lack of training in adequate recycling and the poor infrastructure for waste management. Strategic actions focused on strengthen-ing local capacities and ensuring economic support were proposed. The use of decision-making methods apply-ing …


Use Of Delphi-Ahp Neutrosophic Methods For The Analysis Of School Indicators, Alex Fabian Solano Moreno, Carlos Javier Lizcano Charpeta, Beatrice Del Carmen Viteri Naranjo, Jean Pierre Ramos-Carpio Nov 2024

Use Of Delphi-Ahp Neutrosophic Methods For The Analysis Of School Indicators, Alex Fabian Solano Moreno, Carlos Javier Lizcano Charpeta, Beatrice Del Carmen Viteri Naranjo, Jean Pierre Ramos-Carpio

Neutrosophic Sets and Systems

The study addresses the complex task of analyzing school indicators through the combined application of the Delphi-AHP neutrosophic methods, seeking to overcome the limitations of traditional approaches in educational assessment. The research focuses on the urgent need to develop more robust models that can handle the uncertainty, imprecision, and ambiguity inherent in educational data. Although previous research has been conducted on the analysis of school indicators, conventional approaches fail to effectively integrate the multiple dimensions and degree of uncertainty of the data. This study proposes an innovative solution by integrating neutrosophic tools, which allow for a more flexible and detailed …


Insertion And Use Of Multicriteria Methods For Neutrosophic Judicial Evaluation, Roberto Carlos Jiménez Martinez, María José Calderón Velásquez, Manuel Augusto Suarez Albiñol, Yusleidy Marlie Gordo Gómez Nov 2024

Insertion And Use Of Multicriteria Methods For Neutrosophic Judicial Evaluation, Roberto Carlos Jiménez Martinez, María José Calderón Velásquez, Manuel Augusto Suarez Albiñol, Yusleidy Marlie Gordo Gómez

Neutrosophic Sets and Systems

This study addresses the growing need to integrate multicriteria methods into judicial evaluation, specifically through a neutrosophic approach, to improve the accuracy and reliability of legal decision-making. Today, the judicial system faces critical challenges related to the interpretation of evidence, the consideration of multiple factors, and the uncertainty inherent in complex cases. Although various approaches have been used in judicial evaluation, few effectively address the ambiguity and indeterminacy present in the opinions of judges and experts, leading to fragmented or biased analysis. This study seeks to close that gap by applying neutrosophic multicriteria methods, which allow for a more balanced …


Optimizing Tourism Offers With Copras-Svns For Stress Reduction And Sustainability Promotion, Freddy Anaximandro Álvarez Lema, Manuel Antonio Abarca Zaquinaula, Milton Alberto Sampedro Arrieta, Rodolfo Matius Mendoza Poma Nov 2024

Optimizing Tourism Offers With Copras-Svns For Stress Reduction And Sustainability Promotion, Freddy Anaximandro Álvarez Lema, Manuel Antonio Abarca Zaquinaula, Milton Alberto Sampedro Arrieta, Rodolfo Matius Mendoza Poma

Neutrosophic Sets and Systems

This study focused on the evaluation of tourist packages in the Pichincha region, Ecuador, designed to combine sustainability and stress reduction. Its main objective was to identify the most effective alternatives using mul-ticriteria decision methods, incorporating neutrosophic logic as a key approach. Eight tourist packages were ana-lyzed, integrating activities such as reforestation, meditation, and rural tourism with organic gardens, all aimed at environmental sustainability and the emotional well-being of participants. Using the neutrosophic correlation method, the most relevant criteria for subsequent analysis were selected. The application of the COPRAS-SVNS method determined that the "Eco-destinations with electric bicycle" package represented the …


Enhancing The Teaching-Learning Process Through Neutrosophic Statistical Analysis Of Professional Competencies And Metacognitive Strategies, Dante Manuel Macazana Fernandez, Wilder Fabio Ramos Palacios, Daniel Amílcar Pinto Pagaza,, Mary Liz Mendoza Hidalgo, Tula Margarita Espinoza Moreno, Mayra Susan Albán Taipe Nov 2024

Enhancing The Teaching-Learning Process Through Neutrosophic Statistical Analysis Of Professional Competencies And Metacognitive Strategies, Dante Manuel Macazana Fernandez, Wilder Fabio Ramos Palacios, Daniel Amílcar Pinto Pagaza,, Mary Liz Mendoza Hidalgo, Tula Margarita Espinoza Moreno, Mayra Susan Albán Taipe

Neutrosophic Sets and Systems

In the educational field, teaching effectiveness depends on the interaction between professional competencies and teachers' metacognitive strategies. Therefore, the present study has proposed to evaluate the relationship be-tween professional competencies and metacognitive strategies, by using the management of indeterminacies to improve the teaching-learning process. To this end, the neutrosophic statistics method was applied to analyze data on meta-cognitive competencies and strategies in a group of teachers. Among the results, a general positive relationship was revealed between professional competencies and metacognitive strategies, with significant var-iations in specific areas. Finally, it has been concluded that there is a significant connection, where the …


Ncc: Neutrosophic Control Charts, A Didactic Way To Detect Cardiac Arrhythmias From Reading Electrocardiograms, Lorenzo Cevallos-Torres, Jefferson Núñez-Gaibor, Maikel Leyva-Vasquez, Víctor Gómez-Rodríguez, Franklin Parrales-Bravo, Jesús Hechavarría-Hernández Nov 2024

Ncc: Neutrosophic Control Charts, A Didactic Way To Detect Cardiac Arrhythmias From Reading Electrocardiograms, Lorenzo Cevallos-Torres, Jefferson Núñez-Gaibor, Maikel Leyva-Vasquez, Víctor Gómez-Rodríguez, Franklin Parrales-Bravo, Jesús Hechavarría-Hernández

Neutrosophic Sets and Systems

Cardiac arrhythmias are cardiovascular conditions caused by irregularities in the formation or transmission of electrical impulses. To identify these arrhythmias and determine their origin, an electrocardiogram (ECG) is used, which graphically records the electrical activity responsible for each heartbeat over a short period. This analysis can reveal stochastic changes, introducing a degree of uncertainty. To detect these changes, neutrosophic control charts provide an appropriate statistical tool to assess the stability of the ECG, anticipate potential heart failures, reduce variability in measurements, and, in some cases, make predictions. The results indicate that the proposed model is highly accurate in detecting and …


Neutrosophic Evaluation Through The Pestel Method, Nelly Valeria Vino Ocho, Teresa De Jesús Molino Gutiérrez, Luis Fernando Piñas Piñas, Oscar José Alejo Machado Nov 2024

Neutrosophic Evaluation Through The Pestel Method, Nelly Valeria Vino Ocho, Teresa De Jesús Molino Gutiérrez, Luis Fernando Piñas Piñas, Oscar José Alejo Machado

Neutrosophic Sets and Systems

This study addresses the complexity of assessing key factors in strategic decision-making through PESTEL analy-sis applied with a neutrosophic perspective. In a context of increasing uncertainty, organizations face challenges in accurately interpreting political, economic, social, technological, environmental and legal factors, which are fundamental for sustainable development and informed decision-making. The importance of this topic lies in the need to integrate approaches that not only describe these factors in a static manner, but also address the ambigui-ty and complexity inherent in the variables that compose them. By applying the PESTEL method in its neutro-sophic version, the study aims to go beyond …


Evaluation Of The Impact Of The Use Of Digital Skills On The Substantial Increase In Learning Through The Neutrosophic Pest-Swot Approach, Luis Fernando Blanco Ayala, Ricardo Edilberto Palacios Pérez, Jean Pierre Wong Silva, Bertha Silva Narvaste, Josué Joel Ríos Herrera, Viviana Pastora Panchi Mayo Nov 2024

Evaluation Of The Impact Of The Use Of Digital Skills On The Substantial Increase In Learning Through The Neutrosophic Pest-Swot Approach, Luis Fernando Blanco Ayala, Ricardo Edilberto Palacios Pérez, Jean Pierre Wong Silva, Bertha Silva Narvaste, Josué Joel Ríos Herrera, Viviana Pastora Panchi Mayo

Neutrosophic Sets and Systems

The research focuses on measuring the influence of the use of digital skills on learning, a major issue in current education. The fundamental issue addressed is how digital skills can greatly influence the educational process and the academic success of learners. In the contemporary environment, characterized by rapid technological growth and the increasing integration of digital instruments into the educational sphere, this challenge becomes especially essential. Despite the extensive use of digital technologies, there is a dearth of a comprehensive exam-ination of how these skills influence learning from a multidimensional point of view that incorporates both in-trinsic possibilities and risks. …


Applying Neutroalgebra And Neutrosophic Sentiment Analysis To Assess Last Mile Logistics Impact On Customer Experience, Rosa María Criollo Delgado, Julio Cesar Vidal Rischmoller, Sergio Marcelo Palomino Criollo Nov 2024

Applying Neutroalgebra And Neutrosophic Sentiment Analysis To Assess Last Mile Logistics Impact On Customer Experience, Rosa María Criollo Delgado, Julio Cesar Vidal Rischmoller, Sergio Marcelo Palomino Criollo

Neutrosophic Sets and Systems

The aim of the paper entitled Neutrosophic Sentiment Assessment Using Neutroalgebra Applied to Last Mile Impact on Customer Experience explains the assessment of how factors related to last mile logistics impact cus-tomer perception. While there are many articles and research studies related to last mile logistics, the body of such articles simply focuses on repeating ordinary scope quantitative and qualitative analysis with an urban fo-cus. This paper is intended to be an innovative contribution to the existing body of knowledge by ‘catching the wave’ of the current state of algebra and employing neutrosophy to develop a better understanding and model-ing …


Evaluation Of Anxiety-Producing Factors In The Context Of Dental Care Using Delphi-Ahp Neutrosophic Methods, Christian Esteban Gómez Carrión, Ruth Asela Saravia Alviar, Jessica Haydée Saravia Alviar, Brenda Roxana Vergara Pinto, Elca Rocío Del Águila Gastelu, Secundino Marrero Ramírez Nov 2024

Evaluation Of Anxiety-Producing Factors In The Context Of Dental Care Using Delphi-Ahp Neutrosophic Methods, Christian Esteban Gómez Carrión, Ruth Asela Saravia Alviar, Jessica Haydée Saravia Alviar, Brenda Roxana Vergara Pinto, Elca Rocío Del Águila Gastelu, Secundino Marrero Ramírez

Neutrosophic Sets and Systems

The present study addresses a crucial problem in the field of dental care: the anxiety that patients experience during dental procedures. This worry is crucial considering that anxiety may impair both the patient experience and the efficacy of therapy. Despite the extensive literature on techniques for managing anxiety in medical contexts, there is a notable gap in the integration of systematic approaches that consider both technical and psychological factors. This paper addresses that gap by employing the neutrosophic Delphi-AHP technique, a novel methodology that allows for full evaluation and prioritization of treatments to decrease anxiety. Using a technique that combines …


2-Tuple Linguistic Neutrosophic Numbers And Variance Analysis To Examine Citizenship Formation In The General Studies Programs At The Universities Of Lima, Marco Antonio Tarifeño Ramírez, Ada Lucía Gallegos Ruiz Conejo, Héctor Félix Cerna Maguiña, Nancy Elizabeth Alberca Pintado, Carlos Edwin Rojas Saldívar, Secundino Marrero Ramírez Nov 2024

2-Tuple Linguistic Neutrosophic Numbers And Variance Analysis To Examine Citizenship Formation In The General Studies Programs At The Universities Of Lima, Marco Antonio Tarifeño Ramírez, Ada Lucía Gallegos Ruiz Conejo, Héctor Félix Cerna Maguiña, Nancy Elizabeth Alberca Pintado, Carlos Edwin Rojas Saldívar, Secundino Marrero Ramírez

Neutrosophic Sets and Systems

At all stages of their academic lives, students can benefit from the knowledge gained through collaborative learning. After completing basic training, you will have the opportunity to review historical understanding concepts. Its purpose is to promote the exploration of concepts such as democratic citizenship that can be linked to direct experience of republican history and academic study. The purpose of this study was to examine the relationship between civic education human rights and civic training using Neutrosophic analysis of variance and 2-tuple linguistic neutrosophic numbers. It is assumed that historical awareness and reflection on the natural environment, developed institutionally, in …


Effect Of The 7p'S Of The Marketing Mix On The Sales Strategies Of A Private University: A Comprehensive Analysis Using The Neutrosoph-Ic Pest-Swot Approach, Danny Joseph Anthony Flores Villarruel, Rosa María Criollo Delgado Nov 2024

Effect Of The 7p'S Of The Marketing Mix On The Sales Strategies Of A Private University: A Comprehensive Analysis Using The Neutrosoph-Ic Pest-Swot Approach, Danny Joseph Anthony Flores Villarruel, Rosa María Criollo Delgado

Neutrosophic Sets and Systems

The article focuses on the effect of the 7Ps of the Marketing Mix with respect to the Sales Strategies of a Private University exploring a growing trend in development towards the educational market. Although there have been some recent developments towards most of those substantially engaged with educational marketing, there seems to be a clear lag in research addressing how these variables relate to higher education institutions especially in areas where political-economic, social and technological determinants are of great importance. The study also seeks to address these issues using a neutrosophic PEST-SWOT approach in the hope of position-ing external factors …


Class Name Guided Out-Of-Scope Intent Classification, Chandan Gautam, Sethupathy Parameswaran, Aditya Kane, Yuan Fang, Savitha Ramasamy, Suresh Sundaram, Sunil Kumar Sahu, Xiaoli Li Nov 2024

Class Name Guided Out-Of-Scope Intent Classification, Chandan Gautam, Sethupathy Parameswaran, Aditya Kane, Yuan Fang, Savitha Ramasamy, Suresh Sundaram, Sunil Kumar Sahu, Xiaoli Li

Research Collection School Of Computing and Information Systems

The paper introduces Semantics of Class Labelbased Unsupervised Out of Scope Intent Detection (SCOOS), a novel method aimed at enhancing out-of-scope (OOS) intent classification in task-oriented dialogue systems. Unlike prior approaches that rely solely on indomain (ID) data features, SCOOS leverages semantic cues embedded in class labels to improve classification accuracy. The method entails forming a compact feature space centered around the semantics of class labels by minimizing losses between ID features and class names. SCOOS achieves this by creating a compact feature space centered around class label semantics, achieved through minimizing losses between in-domain (ID) features and class names. …


Large Language Models For Software Engineering: A Systematic Literature Review, Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang Nov 2024

Large Language Models For Software Engineering: A Systematic Literature Review, Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a Systematic Literature Review (SLR) on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We selected and analyzed 395 research articles from January 2017 to January 2024 to answer four key Research Questions (RQs). In RQ1, we categorize different LLMs …


Cirp: Cross‑Item Relational Pre‑Training For Multimodal Product Bundling, Yunshan Ma, Yingzhi He, Wenjun Zhong, Xiang Wang, Roger Zimmermann, Tat-Seng Chua Nov 2024

Cirp: Cross‑Item Relational Pre‑Training For Multimodal Product Bundling, Yunshan Ma, Yingzhi He, Wenjun Zhong, Xiang Wang, Roger Zimmermann, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Product bundling has been a prevailing marketing strategy that is beneficial in the online shopping scenario. Effective product bundling methods depend on high-quality item representations capturing both the individual items' semantics and cross-item relations. However, previous item representation learning methods, either feature fusion or graph learning, suffer from inadequate cross-modal alignment and struggle to capture the cross-item relations for cold-start items. Multimodal pre-train models could be the potential solutions given their promising performance on various multimodal downstream tasks. However, the cross-item relations have been under-explored in the current multimodal pre-train models.To bridge this gap, we propose a novel and simple …


Strength Lies In Differences! Improving Strategy Planning For Non-Collaborative Dialogues Via Diversified User Simulation, Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua Nov 2024

Strength Lies In Differences! Improving Strategy Planning For Non-Collaborative Dialogues Via Diversified User Simulation, Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system’s objectives. This poses two main challenges for existing dialogue agents: 1) The inability to integrate user-specific characteristics into the strategic planning, and 2) The difficulty of training strategic planners that can be generalized to diverse users. To address these challenges, we propose TRIP to enhance the capability in tailored strategic planning, incorporating a user-aware strategic planning module and a population-based training paradigm. Through experiments on benchmark non-collaborative dialogue tasks, we demonstrate the effectiveness …


Thoughts To Target: Enhance Planning For Target-Driven Conversation, Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie Nov 2024

Thoughts To Target: Enhance Planning For Target-Driven Conversation, Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie

Research Collection School Of Computing and Information Systems

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan1. With the aid of corresponding conversational data and support from …


Don’T Just Say “I Don’T Know”! Self-Aligning Large Language Models For Responding To Unknown Questions With Explanations, Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua Nov 2024

Don’T Just Say “I Don’T Know”! Self-Aligning Large Language Models For Responding To Unknown Questions With Explanations, Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer. To avoid providing hallucinated answers to these unknown questions, existing studies typically investigate approaches to refusing to answer these questions. In this work, we propose a novel and scalable self-alignment method to utilize the LLM itself to enhance its response-ability to different types of unknown questions, being capable of not only refusing to answer but also providing explanation to the unanswerability of unknown questions. Specifically, the Self-Align method first employ …


Selective Annotation Via Data Allocation: These Data Should Be Triaged To Experts For Annotation Rather Than The Model, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Ido Dagan Nov 2024

Selective Annotation Via Data Allocation: These Data Should Be Triaged To Experts For Annotation Rather Than The Model, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Ido Dagan

Research Collection School Of Computing and Information Systems

To obtain high-quality annotations under limited budget, semi-automatic annotation methods are commonly used, where a portion of the data is annotated by experts and a model is then trained to complete the annotations for the remaining data. However, these methods mainly focus on selecting informative data for expert annotations to improve the model predictive ability (i.e., triage-to-human data), while the rest of the data is indiscriminately assigned to model annotation (i.e., triage-to-model data). This may lead to inefficiencies in budget allocation for annotations, as easy data that the model could accurately annotate may be unnecessarily assigned to the expert, and …


Beyond Persuasion : Towards Conversational Recommender System With Credible Explanations, Peixin Qin, Chen Huang, Yang Deng, Wenqiang Lei, Tat-Seng Chua Nov 2024

Beyond Persuasion : Towards Conversational Recommender System With Credible Explanations, Peixin Qin, Chen Huang, Yang Deng, Wenqiang Lei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items. While these CRSs are highly persuasive, they can mislead users by incorporating incredible information in their explanations, ultimately damaging the long-term trust between users and the CRS. To address this, we propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS’s explanations during persuasion. It guides the explanation generation through our proposed credibility-aware persuasive strategies and then gradually refines explanations via post-hoc self-reflection. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive …


A Survey Of Ontology Expansion For Conversational Understanding, Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao Nov 2024

A Survey Of Ontology Expansion For Conversational Understanding, Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Research Collection School Of Computing and Information Systems

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art techniques in OnExp for conversational understanding. It categorizes the existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp. By examining the methodologies, benchmarks, and challenges associated with these areas, we highlight several emerging frontiers in OnExp to improve agent performance in real-world …


Consecutive Batch Model Editing With Hook Layers, Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam Nov 2024

Consecutive Batch Model Editing With Hook Layers, Shuaiyi Li, Yang Deng, Deng Cai, Hongyuan Lu, Liang Chen, Wai Lam

Research Collection School Of Computing and Information Systems

As the typical retraining paradigm is unacceptably time- and resource-consuming, researchers are turning to model editing to find an effective way that supports both consecutive and batch scenarios to edit the model behavior directly. Despite all these practical expectations, existing model editing methods fail to realize all of them. Furthermore, the memory demands for such sequential model editing approaches tend to be prohibitive, frequently necessitating an external memory that grows incrementally over time. To cope with these challenges, we propose CoachHooK, a model editing method that simultaneously supports sequential and batch editing. CoachHooK is memory-friendly as it only needs a …


Context-Aware Adapter Tuning For Few-Shot Relation Learning In Knowledge Graphs, Ran Liu, Zhongzhou Liu, Xiaoli Li, Yuan Fang Nov 2024

Context-Aware Adapter Tuning For Few-Shot Relation Learning In Knowledge Graphs, Ran Liu, Zhongzhou Liu, Xiaoli Li, Yuan Fang

Research Collection School Of Computing and Information Systems

Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approaches have emerged, utilizing techniques such as meta-learning. However, the assumption is that novel relations in meta-testing and base relations in meta-training are independently and identically distributed, which may not hold in practice. To address the limitation, we propose RelAdapter, a context-aware adapter for few-shot relation learning in KGs designed to enhance the adaptation process in meta-learning. First, RelAdapter is equipped with a lightweight adapter module that facilitates …