基于Bert预训练模型的虚假新闻文本检测

虚假新闻剥夺了人们获取真相的权利,也给社会和国家带来了许多危害。文中以虚假新闻文本为例,分析和验证了多种预训练语言模型在虚假新闻文本分类上的分类效果。经实验证明,相较于其他语言模型,Bert预训练语言模型取得了较好的结果,预测准确率为86.97%,召回率为88.12%,F1值为87.54%。     

Context-gated knowledge partitioning in categorization.

According to the knowledge partitioning framework, people sometimes master complex tasks by creating multiple independent parcels of partial knowledge. Research has shown that knowledge parcels may contain mutually contradictory information, and that each parcel may be used without regard to knowledge that is demonstrably present in other parcels. This article reports 4 experiments that investigated knowledge partitioning in categorization. When component boundaries of a complex categorization were identified by a context cue, a significant proportion of participants learned partial and independent categorization strategies that were chosen on the basis of context. For those participants, a strategy used in one context was unaffected by knowledge demonstrably present in other contexts, suggesting that knowledge partitioning in categorization can be complete. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Differences in color naming and color salience in Vietnamese and English

The accepted model of color naming postulates that 11 “basic” color terms representing 11 common perceptual experiences show increased processing salience due to a theorized linkage between perception, visual neurophysiology, and cognition. We tested this theory, originally proposed by Berlin and Kay in 1969. Experiment 1 tested salience by comparing unconstrained color naming across two languages, English and Vietnamese. Results were compared with previous research by Berlin and Kay, Boynton and Olson, and colleagues. Experiment 2 validated our stimuli by comparing OSA, Munsell, and newly rendered “basic” exemplars using colorimetry and behavioral measures. Our results show that the relationship between the visual and verbal domains is more complex than current theory acknowledges. An interpoint distance model of color‐naming behavior is proposed as an alternative perspective on color‐naming universality and color‐category structure. © 2003 Wiley Periodicals, Inc. Col Res Appl, 28, 113–138, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.10131     

Class normalization in centroid-based text categorization

Centroid-based categorization is one of the most popular algorithms in text classification. In this approach, normalization is an important factor to improve performance of a centroid-based classifier when documents in text collection have quite different sizes and/or the numbers of documents in classes are unbalanced. In the past, most researchers applied document normalization, e.g., document-length normalization, while some consider a simple kind of class normalization, so-called class-length normalization, to solve the unbalancedness problem. However, there is no intensive work that clarifies how these normalizations affect classification performance and whether there are any other useful normalizations. The purpose of this paper is three folds; (1) to investigate the effectiveness of document- and class-length normalizations on several data sets, (2) to evaluate a number of commonly used normalization functions and (3) to introduce a new type of class normalization, called term-length normalization, which exploits term distribution among documents in the class. The experimental results show that a classifier with weight-merge-normalize approach (class-length normalization) performs better than one with weight-normalize-merge approach (document-length normalization) for the data sets with unbalanced numbers of documents in classes, and is quite competitive for those with balanced numbers of documents. For normalization functions, the normalization based on term weighting performs better than the others on average. For term-length normalization, it is useful for improving classification accuracy. The combination of term- and class-length normalizations outperforms pure class-length normalization and pure term-length normalization as well as unnormalization with the gaps of 4.29%, 11.50%, 30.09%, respectively.     

"Learning myopia: An adaptive recency effect in category learning": Correction to Jones and Sieck (2003).

Reports an error in "Learning myopia: An adaptive recency effect in category learning" by Matt Jones and Winston R. Sieck (Journal of Experimental Psychology: Learning, Memory, and Cognition, 2003[Jul], Vol 29[4], 626-640). On page 633, Table 2, the values in columns (T, P) and (P, T) in the dual condition row incorrectly read .10 and .90, respectively. The correct values are .90 and .10, respectively. (The following abstract of the original article appeared in record 2003-06626-013.) Recency effects (REs) have been well established in memory and probability learning paradigms but have received little attention in category learning research. Extant categorization models predict REs to be unaffected by learning, whereas a functional interpretation of REs, suggested by results in other domains, predicts that people are able to learn sequential dependencies and incorporate this information into their responses. These contrasting predictions were tested in 2 experiments involving a classification task in which outcome sequences were autocorrelated. Experiment 1 showed that reliance on recent outcomes adapts to the structure of the task, in contrast to models' predictions. Experiment 2 provided constraints on how sequential information is learned and suggested possible extensions to current models to account for this learning. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

It's a sign of the kind: Gestures and words guide infants' inductive inferences.

The role of words and gestures in guiding infants' inductive inferences about nonobvious properties was examined. One hundred seventy-two 14-month-olds and 22-month-olds were presented with novel target objects followed by test objects that varied in similarity to the target. Objects were introduced with a novel word or a novel gesture or with no label. When target and test objects were highly similar in shape, both 14- and 22-month-olds inferred that these objects shared a nonobvious property, regardless of whether the objects were labeled with a word or a gesture or with no label. When objects were labeled with the same word, both 14- and 22-month-olds generalized the nonobvious properties to objects that shared minimal perceptual similarity. Finally, when objects were labeled with the same gesture, 14-month-olds, but not 22-month-olds, generalized the nonobvious properties to objects that shared minimal perceptual similarity. These results indicate that 14-month-olds possess a more generalized symbolic system as they will rely on both words and gestures to guide their inferences. By 22-months of age, infants treat words as a privileged referential form when making inductive inferences. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

THE IMPORTANCE OF NEUTRAL EXAMPLES FOR LEARNING SENTIMENT

Most research on learning to identify sentiment ignores "neutral" examples, learning only from examples of significant (positive or negative) polarity. We show that it is crucial to use neutral examples in learning polarity for a variety of reasons. Learning from negative and positive examples alone will not permit accurate classification of neutral examples. Moreover, the use of neutral training examples in learning facilitates better distinction between positive and negative examples.     

基于类间分散度和类内集中度的文本特征选择。

特征选择是文本分类的关键步骤之一,所选特征子集的优劣直接影响文本分类的结果。论文首先定义了两种特征分类能力：一种是特征对类间文档的分散程度,该分散度越大越好;另一种是特征对类内文档的聚集程度,该集中度越大越好。然后把这两种特征影响度有机地结合起来设计了一个新的特征选择方法,该方法能够对所选特征进行综合考虑,从而使获得的特征集具有较好的代表性。仿真实验表明所提特征选择方法在一定程度上能够提高文本分类性能。     

基于SVM的维吾尔文文本分类研究

文本自动分类技术在提高文本信息利用的有效性和准确性上具有重要的现实意义和广阔的应用前景。随着Internet上维吾尔文信息的迅速发展,维吾尔文文本分类成为处理和组织这些大量文本数据的关键技术。研究维吾尔文文本分类相关技术和方法,针对维吾尔文文本在向量空间模型表示下的高维性,本文采用词干提取和χ2统计量相结合的方法对表示空间进行降维。采用SVM算法构造了维吾尔文文本分类器。针对维吾尔文文本分类语料进行的实验结果表明,SVM分类器的MacroF1值达到了84.6%,明显好于kNN方法。