An investigation into feature construction to assist word sense disambiguation

Identifying the correct sense of a word in context is crucial for many tasks in natural language processing (machine translation is an example). State-of-the art methods for Word Sense Disambiguation (WSD) build models using hand-crafted features that usually capturing shallow linguistic information. Complex background knowledge, such as semantic relationships, are typically either not used, or used in specialised manner, due to the limitations of the feature-based modelling techniques used. On the other hand, empirical results from the use of Inductive Logic Programming (ILP) systems have repeatedly shown that they can use diverse sources of background knowledge when constructing models. In this paper, we investigate whether this ability of ILP systems could be used to improve the predictive accuracy of models for WSD. Specifically, we examine the use of a general-purpose ILP system as a method to construct a set of features using semantic, syntactic and lexical information. This feature-set is then used by a common modelling technique in the field (a support vector machine) to construct a classifier for predicting the sense of a word. In our investigation we examine one-shot and incremental approaches to feature-set construction applied to monolingual and bilingual WSD tasks. The monolingual tasks use 32 verbs and 85 verbs and nouns (in English) from the SENSEVAL-3 and SemEval-2007 benchmarks; while the bilingual WSD task consists of 7 highly ambiguous verbs in translating from English to Portuguese. The results are encouraging: the ILP-assisted models show substantial improvements over those that simply use shallow features. In addition, incremental feature-set construction appears to identify smaller and better sets of features. Taken together, the results suggest that the use of ILP with diverse sources of background knowledge provide a way for making substantial progress in the field of WSD.

Electronic Structure and Spectro-Structural Correlations of Fe(III)Zn(II) Biomimetics for Purple Acid Phosphatases: Relevance to DNA Cleavage and Cytotoxic Activity

Purple acid phosphatases (PAPs) are a group of metallohydrolases that contain a dinuclear Fe(II)M(II) center (M(II) = Fe, Mn, Zn) in the active site and are able to catalyze the hydrolysis of a variety of phosphoric acid esters. The dinuclear complex [(H(2)O)Fe(III)(mu-OH)Zn(II)(L-H)](CIO(4))(2) (2) with the ligand 2-[N-bis(2-pyridylmethyl)aminomethyl]-4-methyl-6-[N-(2-pyridylmethyl)(2-hydroxybenzyl) aminomethyl]phenol (H(2)L-H) has recently been prepared and is found to closely mimic the coordination environment of the Fe(III)Zn(II) active site found in red kidney bean PAP (Neves et al. J. Am. Chem. Soc. 2007, 129, 7486). The biomimetic shows significant catalytic activity in hydrolytic reactions. By using a variety of structural, spectroscopic, and computational techniques the electronic structure of the Fe(III) center of this biomimetic complex was determined. In the solid state the electronic ground state reflects the rhombically distorted Fe(III)N(2)O(4) octahedron with a dominant tetragonal compression align ad along the mu-OH-Fe-O(phenolate) direction. To probe the role of the Fe-O(phenolate) bond, the phenolate moiety was modified to contain electron-donating or -withdrawing groups (-CH(3), -H, -Br, -NO(2)) in the 5-position. Tie effects of the substituents on the electronic properties of the biomimetic complexes were studied with a range of experimental and computational techniques. This study establishes benchmarks against accurate crystallographic struck ral information using spectroscopic techniques that are not restricted to single crystals. Kinetic studies on the hydrolysis reaction revealed that the phosphodiesterase activity increases in the order -NO(2)<- Br <- H <- CH(3) when 2,4-bis(dinitrophenyl)phosphate (2,4-bdnpp) was used as substrate, and a linear free energy relationship is found when log(k(cat)/k(0)) is plotted against the Hammett parameter a. However, nuclease activity measurements in the cleavage of double stranded DNA showed that the complexes containing the electron-withdrawing -NO(2) and electron-donating CH3 groups are the most active while the cytotoxic activity of the biomimetics on leukemia and lung tumoral cells is highest for complexes with electron-donating groups.

Performance evaluation of routing protocols for MANETs with known connectivity patterns using evolving graphs

The assessment of routing protocols for mobile wireless networks is a difficult task, because of the networks` dynamic behavior and the absence of benchmarks. However, some of these networks, such as intermittent wireless sensors networks, periodic or cyclic networks, and some delay tolerant networks (DTNs), have more predictable dynamics, as the temporal variations in the network topology can be considered as deterministic, which may make them easier to study. Recently, a graph theoretic model-the evolving graphs-was proposed to help capture the dynamic behavior of such networks, in view of the construction of least cost routing and other algorithms. The algorithms and insights obtained through this model are theoretically very efficient and intriguing. However, there is no study about the use of such theoretical results into practical situations. Therefore, the objective of our work is to analyze the applicability of the evolving graph theory in the construction of efficient routing protocols in realistic scenarios. In this paper, we use the NS2 network simulator to first implement an evolving graph based routing protocol, and then to use it as a benchmark when comparing the four major ad hoc routing protocols (AODV, DSR, OLSR and DSDV). Interestingly, our experiments show that evolving graphs have the potential to be an effective and powerful tool in the development and analysis of algorithms for dynamic networks, with predictable dynamics at least. In order to make this model widely applicable, however, some practical issues still have to be addressed and incorporated into the model, like adaptive algorithms. We also discuss such issues in this paper, as a result of our experience.