Sciweavers

118 search results - page 1 / 24
» Unlabeled data improves word prediction
Sort
View
ICCV
2009
IEEE
14 years 9 months ago
Unlabeled data improves word prediction
Labeling image collections is a tedious task, especially when multiple labels have to be chosen for each image. In this paper we introduce a new framework that extends state of ...
Nicolas Loeff, Ali Farhadi, Ian Endres and David A...
CIKM
2009
Springer
13 years 11 months ago
Combining labeled and unlabeled data with word-class distribution learning
We describe a novel simple and highly scalable semi-supervised method called Word-Class Distribution Learning (WCDL), and apply it the task of information extraction (IE) by utili...
Yanjun Qi, Ronan Collobert, Pavel Kuksa, Koray Kav...
ICDM
2003
IEEE
220views Data Mining» more  ICDM 2003»
13 years 10 months ago
Exploiting Unlabeled Data for Improving Accuracy of Predictive Data Mining
Predictive data mining typically relies on labeled data without exploiting a much larger amount of available unlabeled data. The goal of this paper is to show that using unlabeled...
Kang Peng, Slobodan Vucetic, Bo Han, Hongbo Xie, Z...
ACL
2006
13 years 6 months ago
Boosting Statistical Word Alignment Using Labeled and Unlabeled Data
This paper proposes a semi-supervised boosting approach to improve statistical word alignment with limited labeled data and large amounts of unlabeled data. The proposed approach ...
Hua Wu, Haifeng Wang, Zhan-yi Liu
ACL
2008
13 years 6 months ago
Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
This paper provides evidence that the use of more unlabeled data in semi-supervised learning can improve the performance of Natural Language Processing (NLP) tasks, such as part-o...
Jun Suzuki, Hideki Isozaki