partial supervision
Recently Published Documents


TOTAL DOCUMENTS

33
(FIVE YEARS 7)

H-INDEX

9
(FIVE YEARS 2)

2021 ◽  
pp. 647-657 ◽  
Author(s):  
Lucas Fidon ◽  
Michael Aertsen ◽  
Doaa Emam ◽  
Nada Mufti ◽  
Frédéric Guffens ◽  
...  

2020 ◽  
Vol 34 (05) ◽  
pp. 8616-8623
Author(s):  
Daniel Peterson ◽  
Susan Brown ◽  
Martha Palmer

Dirichlet-multinomial (D-M) mixtures like latent Dirichlet allocation (LDA) are widely used for both topic modeling and clustering. Prior work on constructing Levin-style semantic verb clusters achieves state-of-the-art results using D-M mixtures for verb sense induction and clustering. We add a bias toward known clusters by explicitly labeling a small number of observations with their correct VerbNet class. We demonstrate that this partial supervision guides the resulting clusters effectively, improving the recovery of both labeled and unlabeled classes by 16%, for a joint 12% absolute improvement in F1 score compared to clustering without supervision. The resulting clusters are also more semantically coherent. Although the technical change is minor, it produces a large effect, with important practical consequences for supervised topic modeling in general.


Author(s):  
Hisham Cholakkal ◽  
Guolei Sun ◽  
Salman Khan ◽  
Fahad Shahbaz Khan ◽  
Ling Shao ◽  
...  

Author(s):  
Pengjiang Qian ◽  
Harry Friel ◽  
Melanie S. Traughber ◽  
Ajit Devaraj ◽  
Bryan Traughber ◽  
...  

2019 ◽  
Vol 29 (4) ◽  
pp. 547-560 ◽  
Author(s):  
Padmanaban Sriramakrishnan ◽  
Thiruvenkadam Kalaiselvi ◽  
Karuppanagounder Somasundaram ◽  
Rangasami Rajeswaran

JURNAL BENING ◽  
2018 ◽  
Vol 5 (1) ◽  
pp. 78
Author(s):  
Dhenny Asmarazisa

This study aimed to determine the effect of the principal supervision and motivation to work on teachers performance, both separately (partial) or jointly (Simultaneously) that conducted at SMK Negeri 2 Batam.In this study, 80 teachers were used for sampling that taken from total populations (teachers). While the types of data used from the questionnaires were distributed throughout the samples. Data analysis was performed by descriptive statistics, which were used to describes in providing images of the object under study through the samples or populations of data obtained in the field associated with the relevant theories and techniques of quantitative analysis of the data which was given a score according to the scale of measurement and to test results using SPSS (Statistics Product and Service Solutions).The result of the research conclude that the partial supervision principals (X1) is not positive and significant effect on teacher performance (Y), with test results of 0.643 or 64.3%, while work motivation (X2) and a significant positive effect on teacher performance (Y) as seen from the test results of 0.37 or 3.7%. But simultaneously the principal supervision and motivation positive and significant impact on the performance of the teacher of SMK Negeri 2 Batam Closeness of 0.567 or 56.7% while the remaining amount of 0.433 or 43.3% is influenced by other variables or factors.Keywords: Supervision, Work Motivation, Performance.


Sign in / Sign up

Export Citation Format

Share Document