Multi-documents Automatic Abstracting based on text clustering and semantic analysis

A method of realization of multi-documents Automatic Abstracting based on text clustering and semantic analysis is brought forward, aimed at overcoming shortages of some current methods about multi-documents. The method makes use of semantic analysis and can realize Automatic Abstracting of multi-documents. The algorithm of twice word segmentation based on the title and first-sentences in paragraphs is brought forward. Its precision and recall is above 95%. For a specific domain on plastics, an Automatic Abstracting system named TCAAS is implemented. The precision and recall of multi-document’s Automatic Abstracting is above 75%. And experiments do prove that it is feasible to use the method to develop a domain Automatic Abstracting system, which is valuable for further study in more depth.     

Exploiting constraint inconsistence for dimension selection in subspace clustering: A semi-supervised approach

Selecting correct dimensions is very important to subspace clustering and is a challenging issue. This paper studies semi-supervised approach to the problem. In this setting, limited domain knowledge in the form of space level pair-wise constraints, i.e., must-links and cannot-links, are available. We propose a semi-supervised subspace clustering (S³C) algorithm that exploits constraint inconsistence for dimension selection. Our algorithm firstly correlates globally inconsistent constraints to dimensions in which they are consistent, then unites constraints with common correlating dimensions, and finally forms the subspaces according to the constraint unions. Experimental results show that S³C is superior to the typical unsupervised subspace clustering algorithm FINDIT, and the other constraint based semi-supervised subspace clustering algorithm SC-MINER.     

Validity of the WISC–IV Spanish for a clinically referred sample of Hispanic children.

The Wechsler Intelligence Scale for Children (WISC) is the most commonly used intelligence test for children. Five years ago, a Spanish version of the WISC–IV was published (WISC-IV Spanish; Wechsler, 2005), but a limited amount of published information is available regarding its utility when assessing clinical samples. The current study included 107 children who were Spanish speaking and of Puerto Rican descent that had been administered the WISC–IV Spanish. They were subdivided into a clinical sample of 35 children with diagnoses of various forms of brain dysfunction (primarily learning disability, attention-deficit/hyperactivity disorder, and epilepsy) and a comparison group made up of 72 normal children who were part of the WISC–IV Spanish version standardization sample. Comparisons between these groups and the standardization sample were performed for the WISC–IV Spanish index and subtest scores. Results indicated that the clinical sample performed worse than the comparison samples on the Working Memory and Processing Speed Indexes, although findings varied to some extent depending on whether the clinical group was compared with the normal comparison group or the standardization sample. These findings provide support for the criterion validity of the WISC–IV Spanish when it is used to assess a clinically referred sample with brain dysfunction. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Automatic transcription of continuous speech into syllable-like units for Indian languages

The focus of this paper is to automatically segment and label continuous speech signal into syllable-like units for Indian languages. In this approach, the continuous speech signal is first automatically segmented into syllable-like units using group delay based algorithm. Similar syllable segments are then grouped together using an unsupervised and incremental training (UIT) technique. Isolated style HMM models are generated for each of the clusters during training. During testing, the speech signal is segmented into syllable-like units which are then tested against the HMMs obtained during training. This results in a syllable recognition performance of 42·6% and 39·94% for Tamil and Telugu. A new feature extraction technique that uses features extracted from multiple frame sizes and frame rates during both training and testing is explored for the syllable recognition task. This results in a recognition performance of 48·7% and 45·36%, for Tamil and Telugu respectively. The performance of segmentation followed by labelling is superior to that of a flat start syllable recogniser (27·8%and 28·8%for Tamil and Telugu respectively).     

The developmental relations between conceptual and procedural knowledge: A multimethod approach.

Interactions between conceptual and procedural knowledge influence the development of mathematical competencies. However, after decades of research, these interrelations are still under debate, and empirical results are inconclusive. The authors point out a source of these problems. Different kinds of knowledge and competencies only show up intertwined in behavior, making it hard to measure them validly and independently of each other. A multimethod approach was used to investigate the extent of these problems. A total of 289 fifth and sixth graders’ conceptual and procedural knowledge about decimal fractions was measured by 4 common hypothetical measures of each kind of knowledge. Study 1 tested whether treatments affected the 2 groups of measures in consistent ways. Study 2 assessed, across 3 measurement points, whether conceptual and procedural knowledge could be modeled as latent factors underlying the measures. The results reveal substantial problems with the validities of the measures, which might have been present but gone undetected in previous studies. A solution to these problems is essential for theoretical and practical progress in the field. The potential of the multimethod approach for this enterprise is discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Fast agglomerative clustering using information of k-nearest neighbors

In this paper, we develop a method to lower the computational complexity of pairwise nearest neighbor (PNN) algorithm. Our approach determines a set of candidate clusters being updated after each cluster merge. If the updating process is required for some of these clusters, k-nearest neighbors are found for them. The number of distance calculations for our method is O(N²), where N is the number of data points. To further reduce the computational complexity of the proposed algorithm, some available fast search approaches are used. Compared to available approaches, our proposed algorithm can reduce the computing time and number of distance calculations significantly. Compared to FPNN, our method can reduce the computing time by a factor of about 26.8 for the data set from a real image. Compared with PMLFPNN, our approach can reduce the computing time by a factor of about 3.8 for the same data set.     

Validity and reliability of the Lesbian, Gay, Bisexual Working Alliance Self-Efficacy Scales.

In this paper, the authors report on the development and initial psychometric evaluation of the Lesbian, Gay, and Bisexual Working Alliance Self-Efficacy Scales (LGB-WASES) with data collected from two studies and 534 counseling trainees. Exploratory factor analysis results yielded a 32-item scale with a three-factor model (a) Emotional Bond, (b) Establishing Tasks, and (c) Setting Goals. LGB-WASES scores were internally consistent and remained stable over a 3-week period. Construct validity evidence suggests the LGB-WASES scores were (a) positively related to general perceptions of counseling self-efficacy and multicultural counseling competency, (b) negatively related to attitudes toward lesbians and gay men, and (d) unrelated to social desirability. Recommendations for future research are also discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

CLUSTERING VERY LARGE DATA SETS USING A LOW MEMORY MATRIX FACTORED REPRESENTATION

A scalable method to cluster data sets too large to fit in memory is presented. This method does not depend on random subsampling, but does scan every individual data sample in a deterministic way. The original data are represented in factored form by the product of two matrices, one or both of which is very sparse. This factored form avoids the need to multiply together these two matrices by using a variant of the Principal Direction Divisive Partitioning (PDDP) algorithm which does not depend on computing the distances between the individual samples. The resulting clustering algorithm is Piecemeal PDDP (PMPDDP), in which the original data are broken up into sections which will fit into memory and clustered. The cluster centers are used to create approximations to the original data items, and each original data item is represented by a linear combination of these centers. We evaluate the performance of PMPDDP on three real data sets, and observe that the quality of the clusters of PMPDDP is comparable to PDDP for the data sets examined.     

Examining corporate reputation judgments with generalizability theory.

The researchers used generalizability theory to examine whether reputation judgments about corporations function in a manner consistent with contemporary theory in the corporate-reputation literature. University professors (n = 86) of finance, marketing, and human resources management made repeated judgments about the general reputations of highly visible American companies. Minimal variability in the judgments is explained by items, time, persons, and field of specialization. Moreover, experts from the different specializations reveal considerable agreement in how they weigh different aspects of corporate performance in arriving at their global reputation judgments. The results generally support the theory of the reputation construct and suggest that stable estimates of global reputation can be achieved with a small number of items and experts. (PsycINFO Database Record (c) 2010 APA, all rights reserved)