Within natural language processing, multi-label classification is an important but challenging task. It more complex than single-label since the document representations need to cover fine-grained label information, while labels predicted by model are often related. Recently, large pre-trained models have achieved great performance on tasks, typically using embedding of [CLS] vector as semantic...

This paper evaluates strategies to combine multiple segmentations of the same image, generated for example by different segmentation methods or by different human experts. Three methods are compared, each estimating and using a different level of prior knowledge about the segmenters. These three methods are: simple label averaging (no priors), a binary expectation maximization (EM) method with ...

Standard multi-label learning methods assume fully labeled training data. This assumption however is impractical in many application domains where labels are difficult to collect and missing labels are prevalent. In this paper, we develop a novel conditional restricted Boltzmann machine model to address multi-label learning with incomplete labels. It uses a restricted Boltzmann machine to captu...

BACKGROUND Litigation documents reveal that pharmaceutical companies have paid physicians to promote off-label uses of their products through a number of different avenues. It is unknown whether physicians and scientists who have such conflicts of interest adequately disclose such relationships in the scientific publications they author. METHODS AND FINDINGS We collected whistleblower complai...

Although the internet is used effectively and beneficially in every aspect of life, several users have been experiencing some problems due to excessive and uncontrolled use. While the term "internet addiction" still remains controversial, disturbed family relationships are considered to be a diagnostic criterion. The use of the internet, even in non-excessive levels, is associated with disturba...

We explore how "emotion maps" can be productively used in clinical assessment and clinical practice with families and couples. This graphic participatory method was developed in sociological studies to examine everyday family relationships. Emotion maps enable us to effectively "see" the dynamic experience and emotional repertoires of family life. Through the use of a case example, in this arti...

While a substantial body of literature has examined the effect of fear appeals in advertising, few, if any, studies have looked into the ethicality of using such threatening messages, particularly for socially desirable outcomes. In this paper, a review of the different theories of ethics leads to the development of an empirical study where the effects of using both physically and socially thre...

Dependencies between the labels is commonly regarded as the crucial issue in multilabel classification. Rules provide a natural way for symbolically describing such relationships, for instance, rules with label tests in the body allow for representing directed dependencies like implications, subsumptions, or exclusions. Moreover, rules naturally allow to jointly capture both local and global la...

The people in an image are generally not strangers, but instead often share social relationships such as husband-wife, siblings, grandparent-child, father-child, or mother-child. Further, the social relationship between a pair of people influences the relative position and appearance of the people in the image. This paper explores using familial social relationships as context for recognizing p...

In this work, we study the problem of transductive pairwise classification from pairwise similarities 1. The goal of transductive pairwise classification from pairwise similarities is to infer the pairwise class relationships, to which we refer as pairwise labels, between all examples given a subset of class relationships for a small set of examples, to which we refer as labeled examples. We pr...