In this paper we review some Active Learning experimental results in order to set up the basis for designing an active learning based system for corpus annotation. Based on the experimental data we design a modular system that allows for initially learning fast, but that it is capable of switching to a slower and more precise learning strategy. The system is designed to perform a semantic role ...

In this paper, we present a system for Arabic semantic role labeling (SRL) based on SVMs and standard features. The system is evaluated on the released SEMEVAL 2007 development and test data. The results show an Fβ=1 score of 94.06 on argument boundary detection and an overall Fβ=1 score of 81.43 on the complete semantic role labeling task using gold parse trees.

In large enterprises subject to constant employee turnover and challenging security policies, the administration of Role-based Access Control (RBAC) is a daunting task that is often highly centralized in a small team of security administrators. The aim of this work is to determine why existing models for Administrative Role-based Access Control (ARBAC) have failed to achieve success and thus mo...

In this paper, we present a unified knowledge based approach for sense disambiguation and semantic role labeling. Our approach performs both tasks through a single algorithm that matches candidate semantic interpretations to background knowledge to select the best matching candidate. We evaluate our approach on a corpus of sentences collected from various domains and show how our approach perfo...

Molecular chaperones assist de novo protein folding and facilitate the refolding of stress-denatured proteins. The molecular chaperone concept was coined nearly 35 years ago, and since then, tremendous strides have been made in understanding how these factors support protein folding. Here, we focus on how various chaperone proteins were first identified to play roles in protein folding. Example...

Linear and Hodrick-Prescott detrending methods do not provide a good approximation of the business cycle when output contains a unit root. I use the multivariate Beveridge-Nelson decomposition to document the main patterns of US postwar business cycle when output and some other variables are assumed to be integrated I(1) processes. I show that the business cycle identi...ed in this way displays...

We describe a topic model based approach for selectional preference. Using the topic features generated by an LDA model on the extracted predicate-arguments over the Chinese Gigaword corpus, we show improvement to our state-of-the-art Chinese SRL system by 2.34 F1 points on arguments of nominal predicates, 0.40 F1 point on arguments of verb predicates, and 0.66 F1 point overall. More over, simi...