Gilad Katz

ConSent: Context-based sentiment analysis

Abstract We present ConSent, a novel context-based approach for the task of sentiment analysis. Our approach builds on techniques from the field of information retrieval to identify key terms indicative of the existence of sentiment. We model these terms and the contexts in which they appear and use them to generate features for supervised learning. The two major strengths of the proposed model are its robustness against noise and the easy addition of features from multiple sources to the feature set. Empirical evaluation over multiple real-world domains demonstrates the merit of our approach, compared to state-of the art methods both in noiseless and noisy text.

CoBAn: A context based model for data leakage prevention

A new context-based model (CoBAn) for accidental and intentional data leakage prevention (DLP) is proposed. Existing methods attempt to prevent data leakage by either looking for specific keywords and phrases or by using various statistical methods. Keyword-based methods are not sufficiently accurate since they ignore the context of the keyword, while statistical methods ignore the content of the analyzed text. The context-based approach we propose leverages the advantages of both these approaches. The new model consists of two phases: training and detection. During the training phase, clusters of documents are generated and a graph representation of the confidential content of each cluster is created. This representation consists of key terms and the context in which they need to appear in order to be considered confidential. During the detection phase, each tested document is assigned to several clusters and its contents are then matched to each clusters respective graph in an attempt to determine the confidentiality of the document. Extensive experiments have shown that the model is superior to other methods in detecting leakage attempts, where the confidential information is rephrased or is different from the original examples provided in the learning set.

Analyzing group communication for preventing data leakage via email

Modern business activities rely on extensive email exchange. Various solutions attempt to analyze email exchange in order to prevent emails from being sent to the wrong recipients. However there are still no satisfying solutions; many email addressing mistakes are not detected and in many cases correct recipients are wrongly marked as potential addressing mistakes. In this paper we present a new approach for preventing emails addressing mistakes in organizations. The approach is based on analysis of emails exchange among members of the organization and the identification of groups based on common topics. Each members topics are then used during the enforcement phase for detecting potential leakage. When a new email is composed and about to be sent, each email recipient is analyzed. A recipient is approved if the emails content belongs to at least one of the topics common to the sender and the recipient. We evaluated the new approach using the Enron Email dataset. Our evaluation results suggest that the new approach easily copes with email recipients that have no previous direct connection with the sender.

Using Wikipedia to boost collaborative filtering techniques

One important challenge in the field of recommender systems is the sparsity of available data. This problem limits the ability of recommender systems to provide accurate predictions of user ratings. We overcome this problem by using the publicly available user generated information contained in Wikipedia. We identify similarities between items by mapping them to Wikipedia pages and finding similarities in the text and commonalities in the links and categories of each page. These similarities can be used in the recommendation process and improve ranking predictions. We find that this method is most effective in cases where ratings are extremely sparse or nonexistent. Preliminary experimental results on the MovieLens dataset are encouraging.

Electrical Dispersion Compensation Equalizers in Optical Direct- and Coherent-Detection Systems

We study the performances of several electrical dispersion compensation (EDC) equalizers in the presence of chromatic dispersion (CD) and polarization mode dispersion (PMD) for optical coherent and direct detection on-off keying systems. The EDCs that are analyzed include the decision-feedback equalizer, linear equalizer, and maximum-likelihood sequence estimator (MLSE). We present an inclusive quantitative analysis of the performance difference between the various techniques. The MLSE gives a good indication of the best possible performance

Wikipedia-based query performance prediction

The query-performance prediction task is to estimate retrieval effectiveness with no relevance judgments. Pre-retrieval prediction methods operate prior to retrieval time. Hence, these predictors are often based on analyzing the query and the corpus upon which retrieval is performed. We propose a {\em corpus-independent} approach to pre-retrieval prediction which relies on information extracted from Wikipedia. Specifically, we present Wikipedia-based features that can attest to the effectiveness of retrieval performed in response to a query {\em regardless} of the corpus upon which search is performed. Empirical evaluation demonstrates the merits of our approach. As a case in point, integrating the Wikipedia-based features with state-of-the-art pre-retrieval predictors that analyze the corpus yields prediction quality that is consistently better than that of using the latter alone.

Coherent Compensation for 100G DP-QPSK With One Sample per Symbol Based on Antialiasing Filtering and Blind Equalization MLSE

We propose coherent detection with one sample/symbol. Maximum-likelihood sequence estimation (MLSE) is used to compensate for intersymbol interference introduced by antialiasing filtering. The 100 000-ps/nm chromatic dispersion and 100-ps differential group delay are compensated with 1.5-dB penalty. Blind MLSE equalization is proposed.

Radial Basis Function Network Equalizer for Optical Communication OOK System

In this paper, we introduce a nonlinear equalizer using the radial basis function (RBF) network for electronic dispersion compensation in optical communication systems with on-off keying and a direct-detection receiver. The RB method introduces a nonlinear equalization technique that is suitable for optical communication direct-detection systems that include nonlinear transformation at the photodetector. A bit error rate performance comparison shows that the RBF equalizer outperforms the conventional linear feedforward equalizer. In addition, it is shown that, in optically amplified systems, the RBF equalizer improvement is increased even further. Finally, the feasibility of the RBF method is validated by experimental results.

ExploreKit: Automatic Feature Generation and Selection

Feature generation is one of the challenging aspects of machine learning. We present ExploreKit, a framework for automated feature generation. ExploreKit generates a large set of candidate features by combining information in the original features, with the aim of maximizing predictive performance according to user-selected criteria. To overcome the exponential growth of the feature space, ExploreKit uses a novel machine learning-based feature selection approach to predict the usefulness of new candidate features. This approach enables efficient identification of the new features and produces superior results compared to existing feature selection solutions. We demonstrate the effectiveness and robustness of our approach by conducting an extensive evaluation on 25 datasets and 3 different classification algorithms. We show that ExploreKit can achieve classification-error reduction of 20% overall. Our codeis available at https://github.com/giladkatz/ExploreKit.

A nonlinear electrical equalizer with decision feedback for OOK optical communication systems

In this paper we introduce a nonlinear equalizer using the radial basis function (RBF) network with decision feedback equalizer (DFE) for electronic dispersion compensation in optical communication systems with on-off-keying and a direct detection receiver. The RBF method introduces a non-linear equalization technique suitable for optical communication direct detection systems that include nonlinear transformation at the photodetector. A bit error rate performance comparison shows that the RBF with DFE out performs the RBF without DFE and achieves similar results provided by maximum likelihood sequence estimator.