Levent Ozgur

Followers

Following

Public Views

Ali Alomrani

Tongzhou Mu

Elli Galata

Philipp Dominic Siedler

Xiaowen Huang

Shirin Sohrabi

IBM Research

Wentao Ning

The University of Hong Kong

Guandong Xu

IEEE/CAA J. Autom. Sinica

Xuefei Ning

Interests

Uploads

Papers by Levent Ozgur

DRIFT: Deep Reinforcement Learning for Functional Software Testing

ArXiv, 2020

Efficient software testing is essential for productive software development and reliable user exp... more Efficient software testing is essential for productive software development and reliable user experiences. As human testing is inefficient and expensive, automated software testing is needed. In this work, we propose a Reinforcement Learning (RL) framework for functional software testing named DRIFT. DRIFT operates on the symbolic representation of the user interface. It uses Q-learning through Batch-RL and models the state-action value function with a Graph Neural Network. We apply DRIFT to testing the Windows 10 operating system and show that DRIFT can robustly trigger the desired software functionality in a fully automated manner. Our experiments test the ability to perform single and combined tasks across different applications, demonstrating that our framework can efficiently test software with a large range of testing objectives.

Download

Spam Mail Detection Using Artificial Neural Network and Bayesian Filter

Lecture Notes in Computer Science, 2004

Page 1. ZR Yang et al. (Eds.): IDEAL 2004, LNCS 3177, pp. 505510, 2004. © Springer-Verlag Berlin... more

Text Categorization with Class-Based and Corpus-Based Keyword Selection

Lecture Notes in Computer Science, 2005

In this paper, we examine the use of keywords in text categorization with SVM. In contrast to the... more In this paper, we examine the use of keywords in text categorization with SVM. In contrast to the usual belief, we reveal that using keywords instead of all words yields better performance both in terms of accuracy and time. Unlike the previous studies that focus on keyword selection metrics, we compare the two approaches for keyword selection. In corpus-based approach, a single set of keywords is selected for all classes. In class-based approach, a distinct set of keywords is selected for each class. We perform the experiments with the standard Reuters-21578 dataset, with both boolean and tf-idf weighting. Our results show that although tf-idf weighting performs better, boolean weighting can be used where time and space resources are limited. Corpus-based approach with 2000 keywords performs the best. However, for small number of keywords, class-based approach outperforms the corpus-based approach with the same number of keywords.

Download

Text classification with the support of pruned dependency patterns

Pattern Recognition Letters, 2010

We propose a novel text classification approach based on two main concepts, lexical dependency an... more We propose a novel text classification approach based on two main concepts, lexical dependency and pruning. We extend the standard bag-of-words method by including dependency patterns in the feature vector. We perform experiments with 37 lexical dependencies and the effect of each dependency type is analyzed separately in order to identify the most discriminative dependencies. We analyze the effect of pruning (filtering features with low frequencies) for both word features and dependency features. Parameter tuning is performed with eight different pruning levels to determine the optimal levels. The experiments were repeated on three datasets with different characteristics. We observed a significant improvement on the success rates as well as a reduction on the dimensionality of the feature vector. We argue that, in contrast to the works in the literature, a much higher pruning level should be used in text classification. By analyzing the results from the dataset perspective, we also show that datasets in similar formality levels have similar leading dependencies and show close behavior with varying pruning levels.

Download

Optimization of dependency and pruning usage in text classification

Pattern Analysis and Applications, 2010

In this study, a comprehensive analysis of the lexical dependency and pruning concepts for the te... more In this study, a comprehensive analysis of the lexical dependency and pruning concepts for the text classification problem is presented. Dependencies are included in the feature vector as an extension to the standard bag-of-words approach. The pruning process filters features with low frequencies so that fewer but more informative features remain in the solution vector. The pruning levels for words, dependencies, and dependency combinations for different datasets are analyzed in detail. The main motivation in this work is to make use of dependencies and pruning efficiently in text classification and to achieve more successful results using much smaller feature vector sizes. Three different datasets were used in the experiments and statistically significant improvements for most of the proposed approaches were obtained.

Download

Adaptive anti-spam filtering for agglutinative languages: a special case for Turkish

Pattern Recognition Letters, 2004

We propose anti-spam filtering methods for agglutinative languages in general and for Turkish in ... more We propose anti-spam filtering methods for agglutinative languages in general and for Turkish in particular. The methods are dynamic and are based on Artificial Neural Networks (ANN) and Bayesian Networks. The developed algorithms are user-specific and adapt themselves with the characteristics of the incoming e-mails. The algorithms have two main components. The first one deals with the morphology of the words and the second one classifies the e-mails by using the roots of the words extracted by the morphological analysis. Two ANN structures, single layer perceptron and multi-layer perceptron, are considered and the inputs to the networks are determined using binary model and probabilistic model. Similarly, for Bayesian classification, three different approaches are employed: binary model, probabilistic model, and advanced probabilistic model. In the experiments, a total of 750 e-mails (410 spam and 340 normal) were used and a success rate of about 90% was achieved.

Download

DRIFT: Deep Reinforcement Learning for Functional Software Testing

ArXiv, 2020

Download

Spam Mail Detection Using Artificial Neural Network and Bayesian Filter

Lecture Notes in Computer Science, 2004