The Experts below are selected from a list of 1593 Experts worldwide ranked by ideXlab platform
Luigi Lombardi - One of the best experts on this subject based on the ideXlab platform.
-
Semantic Relevance domain specificity and the sensory functional theory of category specificity
Neuropsychologia, 2007Co-Authors: Giuseppe Sartori, Francesca Gnoato, Ilenia Mariani, Sara Prioni, Luigi LombardiAbstract:According to the sensory/functional theory of Semantic memory, Living items rely more on Sensory knowledge than Non-living ones. The sensory/functional explanation of category-specificity assumes that Semantic features are organised on the basis of their content. We report here a study on DAT patients with impaired performance on Living items and tests of Sensory knowledge, and show that this impairment not only disappears after parcelling out Semantic Relevance, but is also reversed if this parameter is appropriately manipulated. Although Semantic Relevance model predicts these results [Sartori, G., & Lombardi, L. (2004). Semantic Relevance and Semantic disorders. Journal of Cognitive Neuroscience, 16, 439–452], they run counter to both the sensory/functional theory and the domain-specific theory of category-specific impairment.
-
Semantic Relevance, domain specificity and the sensory/functional theory of category-specificity.
Neuropsychologia, 2006Co-Authors: Giuseppe Sartori, Francesca Gnoato, Ilenia Mariani, Sara Prioni, Luigi LombardiAbstract:According to the sensory/functional theory of Semantic memory, Living items rely more on Sensory knowledge than Non-living ones. The sensory/functional explanation of category-specificity assumes that Semantic features are organised on the basis of their content. We report here a study on DAT patients with impaired performance on Living items and tests of Sensory knowledge, and show that this impairment not only disappears after parcelling out Semantic Relevance, but is also reversed if this parameter is appropriately manipulated. Although Semantic Relevance model predicts these results [Sartori, G., & Lombardi, L. (2004). Semantic Relevance and Semantic disorders. Journal of Cognitive Neuroscience, 16, 439–452], they run counter to both the sensory/functional theory and the domain-specific theory of category-specific impairment.
-
Semantic Relevance best predicts normal and abnormal name retrieval
Neuropsychologia, 2005Co-Authors: Giuseppe Sartori, Luigi Lombardi, L MattiuzziAbstract:The Relevance of a Semantic feature measures its contribution to the “core” meaning of a concept. In a naming-to-description task, we investigated the predictive power of Relevance in comparison with frequency, familiarity, typicality, and Age-of-Acquisition. In a group of Alzheimer patients with Semantic disorder, Relevance turned out to be the best predictor of name retrieval accuracy in a naming-to-description task. The same pattern of results was observed in normal controls. Relations between Semantic Relevance and the parameters of the concepts are discussed in order to highlight the mechanism of concept activation in a naming-to-description task. © 2004 Elsevier Ltd. All rights reserved.
-
Semantic Relevance and Semantic Disorders
Journal of Cognitive Neuroscience, 2004Co-Authors: Giuseppe Sartori, Luigi LombardiAbstract:Semantic features are of different importance in concept representation. The concept elephant may be more easily identified from the feature than from the feature . We propose a new model of Semantic memory to measure the Relevance of Semantic features for a concept and use this model to investigate the controversial issue of category specificity. Category-specific patients have an impairment in one domain of knowledge (e.g., living), whereas the other domain (e.g., nonliving) is relatively spared. We show that categories differ in the level of Relevance and that, when concepts belonging to living and nonliving categories are equated to this parameter, the category-specific disorder disappears. Our findings suggest that category specificity, as well as other Semantic-related effects, may be explained by a Semantic memory model in which concepts are represented by Semantic features with associated Relevance values.
Giuseppe Sartori - One of the best experts on this subject based on the ideXlab platform.
-
naming from definition Semantic Relevance and feature type the effects of aging and alzheimer s disease
Neuropsychology (journal), 2011Co-Authors: Frederico J Marques, Stefano F Cappa, Giuseppe SartoriAbstract:Objective: The principal aim of the present study was to evaluate the impact of Semantic Relevance and feature type on the ability to name from definition. Method: Thirty-two normal young subjects (Study 1) and 20 probable Alzheimer's disease patients (pAD) with 20 matched older controls (Study 2) were tested with verbal definitions consisting of 4 features, combining feature type (sensory vs. nonsensory) and Semantic Relevance (high vs. low). The subjects were asked to provide a name corresponding to the definition and to select which individual features they considered most important in justifying their answer. Results: Feature selection results showed that high-Relevance features first (d = 2.13 in Study 1; d = 1.44 in Study 2) and nonsensory features second (d = 0.81 in Study 1; d = 0.36 in Study 2) were the main dimensions driving correct performance. Overall, naming performance was affected by the age of acquisition (AoA) of the concept, and differences between the groups in all measures were mainly quantitative. Conclusions: These findings suggest that Semantic Relevance and feature type are important feature dimensions in conceptual representation and in conceptual access and retrieval. Moreover, results suggest that the former dimension may be more important than the latter, at least in the case of naming from definition. Finally, these results extend previous findings with other tasks, supporting the importance of AoA for correct performance and suggesting that the poorer performance of pAD patients on Semantic tasks may represent an exaggeration of difficulties found also in normal older subjects.
-
Semantic Relevance domain specificity and the sensory functional theory of category specificity
Neuropsychologia, 2007Co-Authors: Giuseppe Sartori, Francesca Gnoato, Ilenia Mariani, Sara Prioni, Luigi LombardiAbstract:According to the sensory/functional theory of Semantic memory, Living items rely more on Sensory knowledge than Non-living ones. The sensory/functional explanation of category-specificity assumes that Semantic features are organised on the basis of their content. We report here a study on DAT patients with impaired performance on Living items and tests of Sensory knowledge, and show that this impairment not only disappears after parcelling out Semantic Relevance, but is also reversed if this parameter is appropriately manipulated. Although Semantic Relevance model predicts these results [Sartori, G., & Lombardi, L. (2004). Semantic Relevance and Semantic disorders. Journal of Cognitive Neuroscience, 16, 439–452], they run counter to both the sensory/functional theory and the domain-specific theory of category-specific impairment.
-
Semantic Relevance, domain specificity and the sensory/functional theory of category-specificity.
Neuropsychologia, 2006Co-Authors: Giuseppe Sartori, Francesca Gnoato, Ilenia Mariani, Sara Prioni, Luigi LombardiAbstract:According to the sensory/functional theory of Semantic memory, Living items rely more on Sensory knowledge than Non-living ones. The sensory/functional explanation of category-specificity assumes that Semantic features are organised on the basis of their content. We report here a study on DAT patients with impaired performance on Living items and tests of Sensory knowledge, and show that this impairment not only disappears after parcelling out Semantic Relevance, but is also reversed if this parameter is appropriately manipulated. Although Semantic Relevance model predicts these results [Sartori, G., & Lombardi, L. (2004). Semantic Relevance and Semantic disorders. Journal of Cognitive Neuroscience, 16, 439–452], they run counter to both the sensory/functional theory and the domain-specific theory of category-specific impairment.
-
Semantic Relevance best predicts normal and abnormal name retrieval
Neuropsychologia, 2005Co-Authors: Giuseppe Sartori, Luigi Lombardi, L MattiuzziAbstract:The Relevance of a Semantic feature measures its contribution to the “core” meaning of a concept. In a naming-to-description task, we investigated the predictive power of Relevance in comparison with frequency, familiarity, typicality, and Age-of-Acquisition. In a group of Alzheimer patients with Semantic disorder, Relevance turned out to be the best predictor of name retrieval accuracy in a naming-to-description task. The same pattern of results was observed in normal controls. Relations between Semantic Relevance and the parameters of the concepts are discussed in order to highlight the mechanism of concept activation in a naming-to-description task. © 2004 Elsevier Ltd. All rights reserved.
-
Semantic Relevance and Semantic Disorders
Journal of Cognitive Neuroscience, 2004Co-Authors: Giuseppe Sartori, Luigi LombardiAbstract:Semantic features are of different importance in concept representation. The concept elephant may be more easily identified from the feature than from the feature . We propose a new model of Semantic memory to measure the Relevance of Semantic features for a concept and use this model to investigate the controversial issue of category specificity. Category-specific patients have an impairment in one domain of knowledge (e.g., living), whereas the other domain (e.g., nonliving) is relatively spared. We show that categories differ in the level of Relevance and that, when concepts belonging to living and nonliving categories are equated to this parameter, the category-specific disorder disappears. Our findings suggest that category specificity, as well as other Semantic-related effects, may be explained by a Semantic memory model in which concepts are represented by Semantic features with associated Relevance values.
Dimitris Plexousakis - One of the best experts on this subject based on the ideXlab platform.
-
CAiSE - The Role of Semantic Relevance in Dynamic User Community Management and the Formulation of Recommendations
Notes on Numerical Fluid Mechanics and Multidisciplinary Design, 2002Co-Authors: Nick Papadopoulos, Dimitris PlexousakisAbstract:In recent years, an increasing interest in recommendation systems has emerged both from the research and the application point of view and in both academic and commercial domains. The majority of comparison techniques used for formulating recommendations are based on set-operations over user-supplied terms or internal product computations on vectors encoding user preferences. In both cases however, the "identical-ness" of terms is examined rather than their actual Semantic Relevance. This paper proposes a recommendation algorithm that is based on the maintenance of user profiles and their dynamic adjustment according to the users" behavior. Moreover, this algorithm relies on the dynamic management of communities, which contain "similar" and "relevant" users and which are created according to a classification algorithm. The algorithm is implemented on top of a community management mechanism. The comparison mechanism used in the context of this work is based on Semantic Relevance between terms, which is evaluated with the use of a glossary of terms.
-
the role of Semantic Relevance in dynamic user community management and the formulation of recommendations
Conference on Advanced Information Systems Engineering, 2002Co-Authors: Nick Papadopoulos, Dimitris PlexousakisAbstract:In recent years, an increasing interest in recommendation systems has emerged both from the research and the application point of view and in both academic and commercial domains. The majority of comparison techniques used for formulating recommendations are based on set-operations over user-supplied terms or internal product computations on vectors encoding user preferences. In both cases however, the "identical-ness" of terms is examined rather than their actual Semantic Relevance. This paper proposes a recommendation algorithm that is based on the maintenance of user profiles and their dynamic adjustment according to the users" behavior. Moreover, this algorithm relies on the dynamic management of communities, which contain "similar" and "relevant" users and which are created according to a classification algorithm. The algorithm is implemented on top of a community management mechanism. The comparison mechanism used in the context of this work is based on Semantic Relevance between terms, which is evaluated with the use of a glossary of terms.
Xiaolong Wang - One of the best experts on this subject based on the ideXlab platform.
-
NTCIR - ICRCS at Intent2: Applying Rough Set and Semantic Relevance for Subtopic Mining.
2020Co-Authors: Xiaoqiang Zhou, Xiaolong Wang, Bo Yuan, Yaoyun ZhangAbstract:The target of the subtopic mining subtask of NTCIR-10 Intent-2 Task is to return a ranked list of subtopics. To this end, this paper proposes a method to apply the rough set theory for redundancy reduction in subtopic mined from webpages. Besides, Semantic similarity is used for subtopic Relevance measure in the re-ranking process, computed with Semantic features extracted by NLP tools and Semantic dictionary. By using the reduction concept of rough set, we first construct rough set based model (RSBM) for subtopic mining. Next, we combine the rough set theory and Semantic Relevance into a new model (RS&SRM). Evaluation results show the effectiveness of our approach compared with a baseline frequency term based model (FTBM). The best performance is achieved by RS&SRM, with I-rec of 0.4046, D-nDCG of 0.4413 and D#-nDCG of 0.4229 on the subtask of Chinese subtopic mining.
-
deep learning approaches to Semantic Relevance modeling for chinese question answer pairs
ACM Transactions on Asian Language Information Processing, 2011Co-Authors: Baoxun Wang, Xiaolong Wang, Deyuan ZhangAbstract:The human-generated question-answer pairs in the Web social communities are of great value for the research of automatic question-answering technique. Due to the large amount of noise information involved in such corpora, it is still a problem to detect the answers even though the questions are exactly located. Quantifying the Semantic Relevance between questions and their candidate answers is essential to answer detection in social media corpora. Since both the questions and their answers usually contain a small number of sentences, the Relevance modeling methods have to overcome the problem of word feature sparsity. In this article, the deep learning principle is introduced to address the Semantic Relevance modeling task. Two deep belief networks with different architectures are proposed by us to model the Semantic Relevance for the question-answer pairs. According to the investigation of the textual similarity between the community-driven question-answering (cQA) dataset and the forum dataset, a learning strategy is adopted to promote our models’ performance on the social community corpora without hand-annotating work. The experimental results show that our method outperforms the traditional approaches on both the cQA and the forum corpora.
-
modeling Semantic Relevance for question answer pairs in web social communities
Meeting of the Association for Computational Linguistics, 2010Co-Authors: Baoxun Wang, Xiaolong WangAbstract:Quantifying the Semantic Relevance between questions and their candidate answers is essential to answer detection in social media corpora. In this paper, a deep belief network is proposed to model the Semantic Relevance for question-answer pairs. Observing the textual similarity between the community-driven question-answering (cQA) dataset and the forum dataset, we present a novel learning strategy to promote the performance of our method on the social community datasets without hand-annotating work. The experimental results show that our method outperforms the traditional approaches on both the cQA and the forum corpora.
-
ACL - Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities
2010Co-Authors: Baoxun Wang, Xiaolong WangAbstract:Quantifying the Semantic Relevance between questions and their candidate answers is essential to answer detection in social media corpora. In this paper, a deep belief network is proposed to model the Semantic Relevance for question-answer pairs. Observing the textual similarity between the community-driven question-answering (cQA) dataset and the forum dataset, we present a novel learning strategy to promote the performance of our method on the social community datasets without hand-annotating work. The experimental results show that our method outperforms the traditional approaches on both the cQA and the forum corpora.
-
SMC - STRank: A SiteRank algorithm using Semantic Relevance and time frequency
2009 IEEE International Conference on Systems Man and Cybernetics, 2009Co-Authors: Qingcai Chen, Xiaolong Wang, Zhiyong Wang, Yonghui WuAbstract:Most of the researches on web information processing are concentrated on the web pages and the hyperlinks among them. One of the important facts that a web page is just one building block of the whole website had been ignored. But the situation is gradually changed in recent years for the needs of website reputation calculation, the high level website structure mining etc. It causes the website ranking become one of the hot research topics and various site ranking algorithms, such as SiteRank, AggregateRank etc., had been proposed. But most of existing website ranking algorithm just take use of website link graphs and the content of websites are usually not put into consideration. It is obviously not enough for a reliable ranking of websites. To address this issue, this paper introduces two content based features, i.e., Semantic Relevance and time frequency and proposes a new STRank algorithm based on these two features. We firstly conduct a series of experiments to verify the feasibility of these two factors in site ranking task. Then the Semantic Relevance is applied in the calculation of transition probability, and the updating frequency of sites is combined into the ranking task. Since traditional Kendall's τ distance and Spearman's Footrule distance is not appropriate for the evaluation of site ranking, we make some modifications accordingly to evaluate website ranking algorithms. Finally, our experiments show that the STRank algorithm outperforms existing approaches on both effectiveness and efficiency.
Heng Tao Shen - One of the best experts on this subject based on the ideXlab platform.
-
ICCV - Leveraging Weak Semantic Relevance for Complex Video Event Classification
2017 IEEE International Conference on Computer Vision (ICCV), 2020Co-Authors: Heng Tao Shen, Chao Li, Zi HuangAbstract:Existing video event classification approaches suffer from limited human-labeled Semantic annotations. Weak Semantic annotations can be harvested from Web-knowledge without involving any human interaction. However such weak annotations are noisy, thus can not be effectively utilized without distinguishing its reliability. In this paper, we propose a novel approach to automatically maximize the utility of weak Semantic annotations (formalized as the Semantic Relevance of video shots to the target event) to facilitate video event classification. A novel attention model is designed to determine the attention scores of video shots, where the weak Semantic Relevance is considered as atten-tional guidance. Specifically, our model jointly optimizes two objectives at different levels. The first one is the classification loss corresponding to video-level groundtruth labels, and the second is the shot-level Relevance loss corresponding to weak Semantic Relevance. We use a long short-term memory (LSTM) layer to capture the temporal information carried by the shots of a video. In each timestep, the LSTM employs the attention model to weight the current shot under the guidance of its weak Semantic Relevance to the event of interest. Thus, we can automatically exploit weak Semantic Relevance to assist video event classification. Extensive experiments have been conducted on three complex large-scale video event datasets i.e., MEDTest14, ActivityNet and FCVID. Our approach achieves the state-of-the-art classification performance on all three datasets. The significant performance improvement upon the conventional attention model also demonstrates the effectiveness of our model.
-
Leveraging Weak Semantic Relevance for Complex Video Event Classification
2017 IEEE International Conference on Computer Vision (ICCV), 2017Co-Authors: Chao Li, Zi Huang, Heng Tao ShenAbstract:Existing video event classification approaches suffer from limited human-labeled Semantic annotations. Weak Semantic annotations can be harvested from Web-knowledge without involving any human interaction. However such weak annotations are noisy, thus can not be effectively utilized without distinguishing its reliability. In this paper, we propose a novel approach to automatically maximize the utility of weak Semantic annotations (formalized as the Semantic Relevance of video shots to the target event) to facilitate video event classification. A novel attention model is designed to determine the attention scores of video shots, where the weak Semantic Relevance is considered as atten-tional guidance. Specifically, our model jointly optimizes two objectives at different levels. The first one is the classification loss corresponding to video-level groundtruth labels, and the second is the shot-level Relevance loss corresponding to weak Semantic Relevance. We use a long short-term memory (LSTM) layer to capture the temporal information carried by the shots of a video. In each timestep, the LSTM employs the attention model to weight the current shot under the guidance of its weak Semantic Relevance to the event of interest. Thus, we can automatically exploit weak Semantic Relevance to assist video event classification. Extensive experiments have been conducted on three complex large-scale video event datasets i.e., MEDTest14, ActivityNet and FCVID. Our approach achieves the state-of-the-art classification performance on all three datasets. The significant performance improvement upon the conventional attention model also demonstrates the effectiveness of our model.
