scholarly journals Dataset Creation Framework for Personalized Type-Based Facet Ranking Tasks Evaluation

2021 ◽  
pp. 27-39
Author(s):  
Esraa Ali ◽  
Annalina Caputo ◽  
Séamus Lawless ◽  
Owen Conlan
Keyword(s):  
2020 ◽  
Vol 2020 (8) ◽  
pp. 188-1-188-7
Author(s):  
Xiaoyu Xiang ◽  
Yang Cheng ◽  
Jianhang Chen ◽  
Qian Lin ◽  
Jan Allebach

Image aesthetic assessment has always been regarded as a challenging task because of the variability of subjective preference. Besides, the assessment of a photo is also related to its style, semantic content, etc. Conventionally, the estimations of aesthetic score and style for an image are treated as separate problems. In this paper, we explore the inter-relatedness between the aesthetics and image style, and design a neural network that can jointly categorize image by styles and give an aesthetic score distribution. To this end, we propose a multi-task network (MTNet) with an aesthetic column serving as a score predictor and a style column serving as a style classifier. The angular-softmax loss is applied in training primary style classifiers to maximize the margin among classes in single-label training data; the semi-supervised method is applied to improve the network’s generalization ability iteratively. We combine the regression loss and classification loss in training aesthetic score. Experiments on the AVA dataset show the superiority of our network in both image attributes classification and aesthetic ranking tasks.


1981 ◽  
Vol 6 (2) ◽  
pp. 235-243 ◽  
Author(s):  
Irving M. Lane ◽  
Robert C. Mathews ◽  
Steven M. Buco

2017 ◽  
Author(s):  
Rory Mitchell ◽  
Eibe Frank

We present a CUDA based implementation of a decision tree construction algorithm within the gradient boosting library XGBoost. The tree construction algorithm is executed entirely on the GPU and shows high performance with a variety of datasets and settings, including sparse input matrices. Individual boosting iterations are parallelized, combining two approaches. An interleaved approach is used for shallow trees, switching to a more conventional radix sort based approach for larger depths. We show speedups of between 3-6x using a Titan X compared to a 4 core i7 CPU, and 1.2x using a Titan X compared to 2x Xeon CPUs (24 cores). We show that it is possible to process the Higgs dataset (10 million instances, 28 features) entirely within GPU memory. The algorithm is made available as a plug-in within the XGBoost library and fully supports all XGBoost features including classification, regression and ranking tasks.


2014 ◽  
Vol 13 (2) ◽  
pp. 276-288
Author(s):  
Derya Çobanoğlu Aktan ◽  
Emrah Oğuzhan Dinçer

The purpose of this study was to investigate pre-service science teachers’ understanding levels of Kepler’s second and third laws. The participants of the study were 38 pre-service science teachers who attended introductory astronomy class in their teacher education program. The participants’ understandings of Kepler’s laws were examined by their answers to ranking tasks, which required participants to rank the situations given in the question, and then to explain the reasons behind their answers. The findings showed that the participants’ understanding levels ranged from partial understanding with alternative conceptions to sound understanding. Moreover the number of the participants with partial understanding with alternative conceptions exceeded the participants with sound understanding. The participants’ explanations to ranking tasks also indicated that although participants knew the classic statements of Kepler’s laws, they had also alternative conceptions. Five different alternative conceptions were identified from the participants’ explanations. Two of them have not been reported in previous studies. Key words: Kepler’s laws, pre-service science teachers, ranking tasks, understanding levels.


2021 ◽  
Author(s):  
Kathryn C. Fisher ◽  
Pascal Haegeli ◽  
Patrick Mair

Abstract. Avalanche warning services publish avalanche condition reports, often called avalanche bulletins, to help backcountry recreationists make informed risk management decisions about when and where to travel in avalanche terrain. To be successful, the information presented in bulletins must be properly understood and applied prior to entering avalanche terrain. However, few avalanche bulletin elements have been empirically tested for their efficacy in communicating hazard information. The objective of this study is to explicitly test the effectiveness of three different graphics representing the aspect and elevation of avalanche problems on users’ ability to apply the information. To address this question, we conducted an online survey that presented participants with one of three graphic renderings of avalanche problem information and asked them to rank a series of route options in order of their exposure to the described hazard. Following completion of route ranking tasks, users were presented with all three graphics and asked to rate how effective they thought the graphics were. Our analysis dataset included responses from 3,056 backcountry recreationists with a variety of backgrounds and avalanche safety training levels. Using a series of generalized linear mixed effects models, our analysis shows that a graphic format that combines the aspect and elevation information for each avalanche problem is the most effective graphic for helping users understand the avalanche hazard conditions because it resulted in higher success in picking the correct exposure ranking, faster completion times, and was rated by users to be the most effective. These results are consistent with existing research on the impact of graphics on cognitive load and can be applied by avalanche warning services to improve the communication of avalanche hazard to readers of their avalanche bulletins.


2006 ◽  
Vol 5 (1) ◽  
pp. 1-22 ◽  
Author(s):  
David W. Hudgins ◽  
Edward E. Prather ◽  
Diane J. Grayson ◽  
Derck P. Smits

1981 ◽  
Vol 5 (4) ◽  
pp. 532-542 ◽  
Author(s):  
Robin Hurwitz Inwald ◽  
N. Dale Bryant

In order to examine the effect of sex of participants on the decision making in small groups, 240 experienced public high school teachers were separated into groups of four, with two males and two females in each group. Half of the teacher groups worked on the same school faculties, while the others were unacquainted with each other. Half of the groups in each setting completed an educationally-related ranking task, while the other half completed a noneducationally-related ranking task. While no significant differences were found between the number of initial suggestions made by males and females which the group accepted, males made significantly more accepted final arguments for items on the ranking tasks than did females ( p < .01). No significant differences were found between groups according to the type of task (educational or noneducational) completed, or familiarity of subjects (same or different school faculties). Results were interpreted in terms of traditional roles and modeling for males and females.


Sign in / Sign up

Export Citation Format

Share Document