Dimensional Semantic Space Research Articles

Point completion by a Stack‐Style Folding Network with multi‐scaled graphical features

AbstractPoint cloud completion is prevalent due to the insufficient results from current point cloud acquisition equipments, where a large number of point data failed to represent a relatively complete shape. Existing point cloud completion algorithms, mostly encoder‐decoder structures with grids transform (also presented as folding operation), can hardly obtain a persuasive representation of input clouds due to the issue that their bottleneck‐shape result cannot tell a precise relationship between the global and local structures. For this reason, this article proposes a novel point cloud completion model based on a Stack‐Style Folding Network (SSFN). Firstly, to enhance the deep latent feature extraction, SSFN enhances the exploitation of shape feature extractor by integrating both low‐level point feature and high‐level graphical feature. Next, a precise presentation is obtained from a high dimensional semantic space to improve the reconstruction ability. Finally, a refining module is designed to make a more evenly distributed result. Experimental results shows that our SSFN produces the most promising results of multiple representative metrics with a smaller scale parameters than current models.

Dual discriminative auto-encoder network for zero shot image recognition

Zero Shot learning (ZSL) aims to use the information of seen classes to recognize unseen classes, which is achieved by transferring knowledge of the seen classes from the semantic embeddings. Since the domains of the seen and unseen classes do not overlap, most ZSL algorithms often suffer from domain shift problem. In this paper, we propose a Dual Discriminative Auto-encoder Network (DDANet), in which visual features and semantic attributes are self-encoded by using the high dimensional latent space instead of the feature space or the low dimensional semantic space. In the embedded latent space, the features are projected to both preserve their original semantic meanings and have discriminative characteristics, which are realized by applying dual semantic auto-encoder and discriminative feature embedding strategy. Moreover, the cross modal reconstruction is applied to obtain interactive information. Extensive experiments are conducted on four popular datasets and the results demonstrate the superiority of this method.

A semi-explicit short text retrieval method combining Wikipedia features

With the advantages such as openness, interactivity, immediacy, and simplicity, the large number of short text data appear in the Web information space. Considering the short length, little information, sparse features and irregular grammar, the traditional information analyzing and retrieval technologies cannot deal with short text effectively. In view of the above problems, in this paper a new short text retrieval method based on the current mainstream semantic knowledge source, Wikipedia, is proposed. To be specific, a semantic feature selection algorithm is proposed to return the top k most relevant Wikipedia concepts as the whole vector space for a given short text. Thus, by analyzing the topic information of the semantic features contained in Wikipedia concepts, we propose some formulas to determine the association coefficient list between different components of the corresponding positions in two different feature vectors. On this basis, a new semantic relatedness assessment method under this lower dimensional semantic space is designed. According to computing and sorting the semantic relatedness between user queries and the target short text, a novel semi-explicit short text retrieval method combining Wikipedia concept feature and the corresponding topic information is proposed. Lastly, based on the experimental results on twitter subsets, we verify that our proposal has advantages over other some current retrieval methods on MAP, P@k and R-Prec, and can return more valid results.

A Hybrid R-BILSTM-C Neural Network Based Text Steganalysis

With the emergence of the generation-based steganography, the traditional text steganalysis methods show the unsatisfactory detection performance as the manually extracted features are simple and non-universal. The recently proposed deep learning-based text steganalysis methods can obtain the great detection accuracy by extracting the high-level features. In this letter, a hybrid text steganalysis method (R-BILSTM-C) is proposed through combining the advantages of Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM) and Convolutional Neural Network (CNN). The proposed method can efficiently capture both local features and long-term semantic information from text to improve the detection accuracy. In the proposed method, the Bi-LSTM architecture is used to capture the long-term semantic information of texts. And the asymmetric convolution kernels with different sizes are applied to extract the local relationship between words. In addition, the high dimensional semantic feature space is visualized. Experimental results show that the proposed method adapts to the different steganographic algorithms efficiently, and achieves the comparable or superior detection performance for the various sentence lengths compared with other state-of-the-art text steganalysis methods.

A procedural texture generation framework based on semantic descriptions

Procedural textures are normally generated from mathematical models with parameters carefully selected by experienced users. However, for naive users, the intuitive way to obtain a desired texture is to provide semantic descriptions such as “regular”, “lacelike”, and “repetitive” and then a procedural model with proper parameters will be automatically suggested to generate the corresponding textures. By contrast, it is less practical for users to learn mathematical models and tune parameters based on multiple examinations of large numbers of generated textures. In this study, we propose a novel framework that generates procedural textures according to user-defined semantic descriptions, and we establish a mapping between procedural models and semantic texture descriptions. First, based on a vocabulary of semantic attributes collected from psychophysical experiments, a multi-label learning method is employed to annotate a large number of textures with semantic attributes to form a semantic procedural texture dataset. Then, we derive a low dimensional semantic space in which the semantic descriptions can be separated from one other. Finally, given a set of semantic descriptions, the diverse properties of the samples in the semantic space can lead the framework to find an appropriate generation model that uses appropriate parameters to produce a desired texture. The experimental results show that the proposed framework is effective and that the generated textures closely correlate with the input semantic descriptions.

Towards a unified model of semantic memory: validation and theoretical implications of the conceptual feature rating space

ABSTRACTThe representation of abstract and concrete concepts has long been a debated question in the literature. In previous work, we created a semantic space which was able to model abstract and concrete concepts in a single multidimensional space. In this study, we tested the validity of our semantic space by comparing it with Latent Semantic Analysis in a word relatedness task during eyetracking. We measured reaction time, gaze measures, and pupil dilation. The results of our study revealed that the newly created space was valid and not just a product of our data. Our ability to simulate a high dimensional semantic space represents a step forward in our understanding of the representation of concepts.

Defining a Conceptual Topography of Word Concreteness: Clustering Properties of Emotion, Sensation, and Magnitude among 750 English Words

Cognitive science has a longstanding interest in the ways that people acquire and use abstract vs. concrete words (e.g., truth vs. piano). One dominant theory holds that abstract and concrete words are subserved by two parallel semantic systems. We recently proposed an alternative account of abstract-concrete word representation premised upon a unitary, high dimensional semantic space wherein word meaning is nested. We hypothesize that a range of cognitive and perceptual dimensions (e.g., emotion, time, space, color, size, visual form) bound this space, forming a conceptual topography. Here we report a normative study where we examined the clustering properties of a sample of English words (N = 750) spanning a spectrum of concreteness in a continuous manner from highly abstract to highly concrete. Participants (N = 328) rated each target word on a range of 14 cognitive dimensions (e.g., color, emotion, valence, polarity, motion, space). The dimensions reduced to three factors: Endogenous factor, Exogenous factor, and Magnitude factor. Concepts were plotted in a unified, multimodal space with concrete and abstract concepts along a continuous continuum. We discuss theoretical implications and practical applications of this dataset. These word norms are freely available for download and use at http://www.reilly-coglab.com/data/.

Learning the Distribution Preserving Semantic Subspace for Clustering

This paper proposes a new clustering method for images called distribution preserving indexing (DPI). It aims to find a lower dimensional semantic space approximating the original image space in the sense of preserving the distribution of the data. In the theory, the intrinsic structure of the data clusters can be described by the distribution of the data effectively. Therefore, the cluster structure of the data in a lower dimensional semantic space derived by the DPI becomes clear. Unlike these distance-based clustering methods, which reveal the intrinsic Euclidean structure of data, our method attempts to discover the intrinsic cluster structure of the data space that actually is the union of some sub-manifolds. Moreover, we propose a revised kernel density estimator for the case of high-dimensional data, which is a crucial step in DPI. In addition, we provide a theoretical analysis of the bound of our method. Finally, the extensive experiments compared with other algorithms, on COIL20, CBCL, and MNIST demonstrate the effectiveness of our proposed approach.

Validating Quantitative Measurement Using Qualitative Data: Combining Rasch Scaling and Latent Semantic Analysis in Psychiatry

An extension of concurrent validity is proposed that uses qualitative data for the purpose of validating quantitative measures. The approach relies on Latent Semantic Analysis (LSA) which places verbal (written) statements in a high dimensional semantic space. Using data from a medical / psychiatric domain as a case study – Near Death Experiences, or NDE – we established concurrent validity by connecting NDErs qualitative (written) experiential accounts with their locations on a Rasch scalable measure of NDE intensity. Concurrent validity received strong empirical support since the variance in the Rasch measures could be predicted reliably from the coordinates of their accounts in the LSA derived semantic space (R2 = 0.33). These coordinates also predicted NDErs age with considerable precision (R2 = 0.25). Both estimates are probably artificially low due to the small available data samples (n = 588). It appears that Rasch scalability of NDE intensity is a prerequisite for these findings, as each intensity level is associated (at least probabilistically) with a well- defined pattern of item endorsements.

Multidimensional Latent Semantic Analysis Using Term Spatial Information

In this paper, we consider the problem of in-depth document analysis. In particular, we propose a novel document analysis method, named multidimensional latent semantic analysis (MDLSA), which enables us to mine local information efficiently from a document with respect to term associations and spatial distributions. MDLSA works by first partitioning each document into paragraphs and building a term affinity graph, which represents the frequency of term cooccurrence in a paragraph. We then conduct a 2-D principal component analysis to achieve an optimal semantic mapping. This analysis involves finding the leading eigenvectors of the sample covariance matrix of a training set to characterize the lower dimensional semantic space. A hybrid document similarity measure is designed to further improve the performance of this framework. Our algorithm is examined in two document applications: retrieval and classification. Experimental results demonstrate that the proposed technique outperforms current algorithms with respect to accuracy and computational efficiency.

Abstract conceptual feature ratings: the role of emotion, magnitude, and other cognitive domains in the organization of abstract conceptual knowledge

This study harnessed control ratings of the contribution of different types of information (sensation, action, emotion, thought, social interaction, morality, time, space, quantity, and polarity) to 400 individual abstract and concrete verbal concepts. These abstract conceptual feature (ACF) ratings were used to generate a high dimensional semantic space, from which Euclidean distance measurements between individual concepts were extracted as a metric of the semantic relatedness of those words. The validity of these distances as a marker of semantic relatedness was then tested by evaluating whether they could predict the comprehension performance of a patient with global aphasia on two verbal comprehension tasks. It was hypothesized that if the high-dimensional space generated from ACF control ratings approximates the organization of abstract conceptual space, then words separated by small distances should be more semantically related than words separated by greater distances, and should therefore be more difficult to distinguish for the comprehension-impaired patient, SKO. SKO was significantly worse at identifying targets presented within word pairs with low ACF distances. Response accuracy was not predicted by Latent Semantic Analysis (LSA) cosines, any of the individual feature ratings, or any of the background variables. It is argued that this novel rating procedure provides a window on the semantic attributes of individual abstract concepts, and that multiple cognitive systems may influence the acquisition and organization of abstract conceptual knowledge. More broadly, it is suggested that cognitive models of abstract conceptual knowledge must account for the representation not only of the relationships between abstract concepts but also of the attributes which constitute those individual concepts.

Effective Search of Color-Spatial Image Using Semantic Indexing

Most of the data storedin libraries are in digital formwill contain either pictures or video, which is tough to search or browse.Methods which are automatic for searching picture collections made large use of color histograms, because they are very strong to wide changes in viewpoint, and can be calculated trivially. However, color histograms unable to present spatial data , and therefore tend to give lesser results. By using combination of color information with spatial layout w e have developed several methods , while retrieving the advantages of histograms. A method computes a given color as a function of the distance between two pixels, which we call a color correlogram. We propose a color-based image descriptor that can be used for image indexing based on high -level semantic concepts. The descriptor is based on Kobayashi’s Color Image Scale, which is a system that includes 130 basic colors combined in 1180 three-color combinations. The words are represented in a two dimensional semantic space into groups based on perceived similarity. The modified approach for statistical analysis of pictures involves transformations of ordinary RGB histograms.Then a semantic image descriptor is der ived, containing semantic data about both color combinations and single colors in the image.

A novel dual wing harmonium model aided by 2-D wavelet transform subbands for document data mining

A novel dual wing harmonium model that integrates multiple features including term frequency features and 2-D wavelet transform features into a low dimensional semantic space is proposed for the applications of document classification and retrieval. Terms are extracted from the graph representation of document by employing weighted feature extraction method. 2-D wavelet transform is used to compress the graph due to its sparseness while preserving the basic document structure. After transform, low-pass subbands are stacked to represent the term associations in a document. We then develop a new dual wing harmonium model projecting these multiple features into low dimensional latent topics with different probability distributions assumption. Contrastive divergence algorithm is used for efficient learning and inference. We perform extensive experimental verification in document classification and retrieval, and comparative results suggest that the proposed method delivers better performance than other methods.

A new dual wing harmonium model for document retrieval

A new dual wing harmonium model that integrates term frequency features and term connection features into a low dimensional semantic space without increase of computation load is proposed for the application of document retrieval. Terms and vectorized graph connectionists are extracted from the graph representation of document by employing weighted feature extraction method. We then develop a new dual wing harmonium model projecting these multiple features into low dimensional latent topics with different probability distributions assumption. Contrastive divergence algorithm is used for efficient learning and inference. We perform extensive experimental verification, and the comparative results suggest that the proposed method is accurate and computationally efficient for document retrieval.

An intelligent information agent for document title classification and filtering in document-intensive domains

Effective decision making is based on accurate and timely information. However, human decision makers are often overwhelmed by the huge amount of electronic data these days. The main contribution of this paper is the development of effective information agents which can autonomously classify and filter incoming electronic data on behalf of their human users. The proposed information agents are innovative because they can quickly classify electronic documents solely based on the short titles of these documents. Moreover, supervised learning is not required to train the classification models of these agents. Document classification is based on information inference conducted over a high dimensional semantic information space. What is more, a belief revision mechanism continuously maintains a set of user preferred information categories and filter documents with respect to these categories. Preliminary experimental results show that our document classification and filtering mechanism outperforms the Support Vector Machines (SVM) model which is regarded as one of the best performing classifiers.

Towards Operational Abduction from a Cognitive Perspective

Diminishing awareness is a consequence of the information explosion: disciplines are becoming increasingly specialized; individuals and groups are becoming ever more insular. This article considers how awareness can be enhanced via operational abductive systems. The goal is to generate and justify suggestions which can span disparate islands of knowledge. Knowledge representation is motivated from a cognitive perspective. Words and concepts are represented as vectors in a high dimensional semantic space automatically derived from a text corpus. Various mechanisms will be presented for computing suggestions from semantic space: information flow, semantic similarity, pre-inductive generalization. The overall goal of this article is to introduce semantic space to the model-based reasoning and abduction community and to illustrate its potential for principled, operational abduction by semi-automatically replicating the Swanson Raynaud/fish oil discovery in medical text.

Abduction in Semantic Space: Towards a Logic of Discovery

Diminishing awareness is a consequence of the information explosion: disciplines are becoming increasingly specialized; individuals and groups are becoming ever more insular. This paper considers how awareness can be enhanced via abductive knowledge discovery the goal of which is to produce suggestions which can span disparate islands of knowledge. Knowledge representation is motivated from a cognitive perspective. Words and concepts are represented as vectors in a high dimensional semantic space automatically derived from a text corpus. Information flow computation between vectors is proposed as a means of suggesting potentially interesting implicit associations between concepts. Information flow is applied to computational scientific discovery by attempting to simulate Swanson's Raynaud-fish oil discovery in medical texts. Both automatic and semi-automatic attempts were studied and compared against suggestions computed via semantic association. Even though this work is preliminary and speculative in nature, there is some justification to believe that appropriate suggestions (hypotheses) can be “abduced” from semantic space.

Towards context sensitive information inference

AbstractHumans can make hasty, but generally robust judgements about what a text fragment is, or is not, about. Such judgements are termed information inference. This article furnishes an account of information inference from a psychologistic stance. By drawing on theories from nonclassical logic and applied cognition, an information inference mechanism is proposed that makes inferences via computations of information flow through an approximation of a conceptual space. Within a conceptual space information is represented geometrically. In this article, geometric representations of words are realized as vectors in a high dimensional semantic space, which is automatically constructed from a text corpus. Two approaches were presented for priming vector representations according to context. The first approach uses a concept combination heuristic to adjust the vector representation of a concept in the light of the representation of another concept. The second approach computes a prototypical concept on the basis of exemplar trace texts and moves it in the dimensional space according to the context. Information inference is evaluated by measuring the effectiveness of query models derived by information flow computations. Results show that information flow contributes significantly to query model effectiveness, particularly with respect to precision. Moreover, retrieval effectiveness compares favorably with two probabilistic query models, and another based on semantic association. More generally, this article can be seen as a contribution towards realizing operational systems that mimic text‐based human reasoning.

CONCEPTUAL MAPPING OF A DATABASE IN THE HUMANITIES: FIRST RESULTS OF AN EXPERIMENT WITH SOPHIA

The idea of conceptual mapping goes back to the semantic differential and conceptual clustering. Using multivariate statistical techniques, one can map a dispersion of texts onto another dispersion of their content indicators, such as keywords. The resulting configurations of texts/indicators differ from one another according to their meaning, expressed in terms of co‐ordinates of a semantic field. We suggest that by using principal component analysis, one can design a user‐friendly semantic space which can be navigated. Further, to learn the names of embedded magnitudes in semantic space, the idea of conceptual clustering is used in a broader context. This is a two‐mode statistical approach, grouping both documents and their index terms at the same time. By observing the agglomerations of narrower, related terms over a corpus, one arrives at broader, more general thesaurus entries which denote and conceptualise the major dimensions of semantic space.

Consistency of Factor Structure on the Semantic Differential: An Analysis of Three Adult Samples

Piotrowski (1983a, 1984) reported on variance in Osgood's (1957) formulation of three dimensions of semantic space on the semantic differential technique with a fifth grade sample. The current study was concerned with the consistency of factor structure in three adult samples using three different concepts: THE UNIVERSITY OF WEST FLORIDA, DEATH, and MYSELF. Results indicated consistency for the predicted Evaluation dimension (Factor I) and moderate consistency for both Potency and Activity dimensions across the three samples. However, some scales tended to be loaded significantly on more than one factor; this was particularly evident for the Evaluation dimension in that several non-Evaluative scales at times weighted on Factor I. Although the findings indicated a slight increase in factor invariance when compared to Piotrowski's earlier work with children, researchers are still cautioned to subject their semantic differential data to factorial methods so as to enhance the validity of their results.