Lexical database enrichment through semi-automated morphological analysis

Derivational morphology proposes meaningful connections between words and is largely unrepresented in lexical databases. This thesis presents a project to enrich a lexical database with morphological links and to evaluate their contribution to disambiguation. A lexical database with sense distinctions was required. WordNet was chosen because of its free availability and widespread use. Its suitability was assessed through critical evaluation with respect to specifications and criticisms, using a transparent, extensible model. The identification of serious shortcomings suggested a portable enrichment methodology, applicable to alternative resources. Although 40% of the most frequent words are prepositions, they have been largely ignored by computational linguists, so addition of prepositions was also required. The preferred approach to morphological enrichment was to infer relations from phenomena discovered algorithmically. Both existing databases and existing algorithms can capture regular morphological relations, but cannot capture exceptions correctly; neither of them provide any semantic information. Some morphological analysis algorithms are subject to the fallacy that morphological analysis can be performed simply by segmentation. Morphological rules, grounded in observation and etymology, govern associations between and attachment of suffixes and contribute to defining the meaning of morphological relationships. Specifying character substitutions circumvents the segmentation fallacy. Morphological rules are prone to undergeneration, minimised through a variable lexical validity requirement, and overgeneration, minimised by rule reformulation and restricting monosyllabic output. Rules take into account the morphology of ancestor languages through co-occurrences of morphological patterns. Multiple rules applicable to an input suffix need their precedence established. The resistance of prefixations to segmentation has been addressed by identifying linking vowel exceptions and irregular prefixes. The automatic affix discovery algorithm applies heuristics to identify meaningful affixes and is combined with morphological rules into a hybrid model, fed only with empirical data, collected without supervision. Further algorithms apply the rules optimally to automatically pre-identified suffixes and break words into their component morphemes. To handle exceptions, stoplists were created in response to initial errors and fed back into the model through iterative development, leading to 100% precision, contestable only on lexicographic criteria. Stoplist length is minimised by special treatment of monosyllables and reformulation of rules. 96% of words and phrases are analysed. 218,802 directed derivational links have been encoded in the lexicon rather than the wordnet component of the model because the lexicon provides the optimal clustering of word senses. Both links and analyser are portable to an alternative lexicon. The evaluation uses the extended gloss overlaps disambiguation algorithm. The enriched model outperformed WordNet in terms of recall without loss of precision. Failure of all experiments to outperform disambiguation by frequency reflects on WordNet sense distinctions.

Use of fundus imaging in quantification of age-related macular change

This review will discuss the use of manual grading scales, digital photography, and automated image analysis in the quantification of fundus changes caused by age-related macular disease. Digital imaging permits processing of images for enhancement, comparison, and feature quantification, and these techniques have been investigated for automated drusen analysis. The accuracy of automated analysis systems has been enhanced by the incorporation of interactive elements, such that the user is able to adjust the sensitivity of the system, or manually add and remove pixels. These methods capitalize on both computer and human image feature recognition and the advantage of computer-based methodologies for quantification. The histogram-based adaptive local thresholding system is able to extract useful information from the image without being affected by the presence of other structures. More recent developments involve compensation for fundus background reflectance, which has most recently been combined with the Otsu method of global thresholding. This method is reported to provide results comparable with manual stereo viewing. Developments in this area are likely to encourage wider use of automated techniques. This will make the grading of photographs easier and cheaper for clinicians and researchers. © 2007 Elsevier Inc. All rights reserved.

Top-down lipidomics of low density lipoprotein reveal altered lipid profiles in advanced chronic kidney disease

This study compared the molecular lipidomic profi le of LDL in patients with nondiabetic advanced renal disease and no evidence of CVD to that of age-matched controls, with the hypothesis that it would reveal proatherogenic lipid alterations. LDL was isolated from 10 normocholesterolemic patients with stage 4/5 renal disease and 10 controls, and lipids were analyzed by accurate mass LC/MS. Top-down lipidomics analysis and manual examination of the data identifi ed 352 lipid species, and automated comparative analysis demonstrated alterations in lipid profi le in disease. The total lipid and cholesterol content was unchanged, but levels of triacylglycerides and N -acyltaurines were signifi cantly increased, while phosphatidylcholines, plasmenyl ethanolamines, sulfatides, ceramides, and cholesterol sulfate were signifi cantly decreased in chronic kidney disease (CKD) patients. Chemometric analysis of individual lipid species showed very good discrimination of control and disease sample despite the small cohorts and identifi ed individual unsaturated phospholipids and triglycerides mainly responsible for the discrimination. These fi ndings illustrate the point that although the clinical biochemistry parameters may not appear abnormal, there may be important underlying lipidomic changes that contribute to disease pathology. The lipidomic profi le of CKD LDL offers potential for new biomarkers and novel insights into lipid metabolism and cardiovascular risk in this disease. -Reis, A., A. Rudnitskaya, P. Chariyavilaskul, N. Dhaun, V. Melville, J. Goddard, D. J. Webb, A. R. Pitt, and C. M. Spickett. Topdown lipidomics of low density lipoprotein reveal altered lipid profi les in advanced chronic kidney disease. J. Lipid Res. 2015.

The benefit of combining standard automated perimetry and multifocal visual evoked potential hemifield intersector analysis in suspecious glaucomatous visual field defects

Several analysis protocols have been tested to identify early visual field losses in glaucoma patients using the mfVEP technique, some were successful in detection of field defects, which were comparable to the standard SAP visual field assessment, and others were not very informative and needed more adjustment and research work. In this study we implemented a novel analysis approach and evaluated its validity and whether it could be used effectively for early detection of visual field defects in glaucoma. The purpose of this study is to examine the benefit of adding mfVEP hemifield Intersector analysis protocol to the standard HFA test when there is suspicious glaucomatous visual field loss. 3 groups were tested in this study; normal controls (38 eyes), glaucoma patients (36 eyes) and glaucoma suspect patients (38 eyes). All subjects had a two standard Humphrey visual field HFA test 24-2, optical coherence tomography of the optic nerve head, and a single mfVEP test undertaken in one session. Analysis of the mfVEP results was done using the new analysis protocol; the Hemifield Sector Analysis HSA protocol. The retinal nerve fibre (RNFL) thickness was recorded to identify subjects with suspicious RNFL loss. The hemifield Intersector analysis of mfVEP results showed that signal to noise ratio (SNR) difference between superior and inferior hemifields was statistically significant between the 3 groups (ANOVA p<0.001 with a 95% CI). The difference between superior and inferior hemispheres in all subjects were all statistically significant in the glaucoma patient group 11/11 sectors (t-test p<0.001), partially significant 5/11 in glaucoma suspect group (t-test p<0.01) and no statistical difference between most sectors in normal group (only 1/11 was significant) (t-test p<0.9). Sensitivity and specificity of the HSA protocol in detecting glaucoma was 97% and 86% respectively, while for glaucoma suspect were 89% and 79%. The use of SAP and mfVEP results in subjects with suspicious glaucomatous visual field defects, identified by low RNFL thickness, is beneficial in confirming early visual field defects. The new HSA protocol used in the mfVEP testing can be used to detect glaucomatous visual field defects in both glaucoma and glaucoma suspect patient. Using this protocol in addition to SAP analysis can provide information about focal visual field differences across the horizontal midline, and confirm suspicious field defects. Sensitivity and specificity of the mfVEP test showed very promising results and correlated with other anatomical changes in glaucoma field loss. The Intersector analysis protocol can detect early field changes not detected by standard HFA test.

Corpus, collocation, and lexical sets

This paper is a progress report on a research path I first outlined in my contribution to “Words in Context: A Tribute to John Sinclair on his Retirement” (Heffer and Sauntson, 2000). Therefore, I first summarize that paper here, in order to provide the relevant background. The second half of the current paper consists of some further manual analyses, exploring various parameters and procedures that might assist in the design of an automated computational process for the identification of lexical sets. The automation itself is beyond the scope of the current paper.

Expert systems for fault analysis

The initial aim of this research was to investigate the application of expert Systems, or Knowledge Base Systems technology to the automated synthesis of Hazard and Operability Studies. Due to the generic nature of Fault Analysis problems and the way in which Knowledge Base Systems work, this goal has evolved into a consideration of automated support for Fault Analysis in general, covering HAZOP, Fault Tree Analysis, FMEA and Fault Diagnosis in the Process Industries. This thesis described a proposed architecture for such an Expert System. The purpose of the System is to produce a descriptive model of faults and fault propagation from a description of the physical structure of the plant. From these descriptive models, the desired Fault Analysis may be produced. The way in which this is done reflects the complexity of the problem which, in principle, encompasses the whole of the discipline of Process Engineering. An attempt is made to incorporate the perceived method that an expert uses to solve the problem; keywords, heuristics and guidelines from techniques such as HAZOP and Fault Tree Synthesis are used. In a truly Expert System, the performance of the system is strongly dependent on the high quality of the knowledge that is incorporated. This expert knowledge takes the form of heuristics or rules of thumb which are used in problem solving. This research has shown that, for the application of fault analysis heuristics, it is necessary to have a representation of the details of fault propagation within a process. This helps to ensure the robustness of the system - a gradual rather than abrupt degradation at the boundaries of the domain knowledge.

Base modified peptidic nucleic acids: synthesis and crystallographic analysis of intermediates

Peptidic Nucleic Acids (PNAs) are achiral, uncharged nucleic add mimetics, with a novel backbone composed of N-(2-aminoethyl)glycine units attached to the DNA bases through carboxymethylene linkers. With the aim of extending and improving upon the molecular recognition properties of PNAs, the aim of this work was to synthesjse PNA building block intermediates containing a series of substituted purine bases for subsequent use in automated PNA synthesis. Four purine bases: 2,6~diaminopurine (D), isoGuanine (isoG), xanthine (X) and hypoxanthine (H) were identified for incorporation into PNAs targeted to DNA, with the promise of increased hybrid stability over extended pH ranges together with improvements over the use of adenine (A) in duplex formation, and cytosine (C) in triplex formation. A reliable, high-yielding synthesis of the PNA backbone component N -('2- butyloxycarbonyl-aminoethyl)glycinate ethyl ester was establishecl. The precursor N~(2-butyloxycarbonyl)amino acetonitrile was crystallised and analysed by X-ray crystallography for the first time. An excellent refinement (R = 0.0276) was attained for this structure, allowing comparisons with known analogues. Although chemical synthesis of pure, fully-characterised PNA monomers was not achieved, chemical synthesis of PNA building blocks composed of diaminopurine, xanthine and hypoxanthine was completely successful. In parallel, a second objective of this work was to characterise and evaluate novel crystalline intermediates, which formed a new series of substituted purine bases, generated by attaching alkyl substituents at the N9 or N7 sites of purine bases. Crystallographic analysis was undertaken to probe the regiochemistry of isomers, and to reveal interesting structural features of the new series of similarly-substituted purine bases. The attainment of the versatile synthetic intermediate 2,6-dichloro~9- (carboxymethyl)purine ethyl ester, and its homologous regioisomers 6-chloro~9- (carboxymethyl)purine ethyl ester and 6-chloro-7-(carboxymethyl)purine ethyl ester, necessitated the use of X-ray crystallographic analysis for unambiguous structural assignment. Successful refinement of the disordered 2,6-diamino-9-(carboxymethyl) purine ethyl ester allowed comparison with the reported structure of the adenine analogue, ethyl adenin-9-yl acetate. Replacement of the chloro moieties with amino, azido and methoxy groups expanded the internal angles at their point of attachment to the purine ring. Crystallographic analysis played a pivotal role towards confirming the identity of the peralkylated hypoxanthine derivative diethyl 6-oxo-6,7-dihydro-3H-purlne~3,7~djacetate, where two ethyl side chains were found to attach at N3 and N7,

Automated synthesis and evaluation of potential new anti-microbial agents

A series of N1-benzylideneheteroarylcarboxamidrazones was prepared in an automated fashion, and tested against Mycobacterium fortuitum in a rapid screen for antimycobacterial activity. Many of the compounds from this series were also tested against Mycobacterium tuberculosis, and the usefulness as M.fortuitum as a rapid, initial screen for anti-tubercular activity evaluated. Various deletions were made to the N1-benzylideneheteroarylcarboxamidrazone structure in order to establish the minimum structural requirements for activity. The N1-benzylideneheteroarylcarbox-amidrazones were then subjected to molecular modelling studies and their activities against M.fortuitum and M.tuberculosis were analysed using quantitative structure-analysis relationship (QSAR) techniques in the computational package TSAR (Oxford Molecular Ltd.). A set of equations predictive of antimycobacterial activity was hereby obtained. The series of N1-benzylidenehetero-arylcarboxamidrazones was also tested against a multidrug-resistant strain of Staphylococcus aureus (MRSA), followed by a panel of Gram-positive and Gram-negative bacteria, if activity was observed for MRSA. A set of antimycobacterial N1-benzylideneheteroarylcarboxamidrazones was hereby discovered, the best of which had MICs against m. fortuitum in the range 4-8μgml-1 and displayed 94% inhibition of M.tuberculosis at a concentration of 6.25μgml-1. The antimycobacterial activity of these compounds appeared to be specific, since the same compounds were shown to be inactive against other classes of organisms. Compounds which were found to be sufficiently active in any screen were also tested for their toxicity against human mononuclear leucocytes. Polyethylene glycol (PEG) was used as a soluble polymeric support for the synthesis of some fatty acid derivatives, containing an isoxazoline group, which may inhibit mycolic acid synthesis in mycobacteria. Both the PEG-bound products and the cleaved, isolated products themselves were tested against M.fortuitum and some low levels of antimycobacterial activity were observed, which may serve as lead compounds for further studies.

An experimental analysis of operating conditions in cold roll-forming

A detailed literature survey confirmed cold roll-forming to be a complex and little understood process. In spite of its growing value, the process remains largely un-automated with few principles used in set-up of the rolling mill. This work concentrates on experimental investigations of operating conditions in order to gain a scientific understanding of the process. The operating conditions are; inter-pass distance, roll load, roll speed, horizontal roll alignment. Fifty tests have been carried out under varied operating conditions, measuring section quality and longitudinal straining to give a picture of bending. A channel section was chosen for its simplicity and compatibility with previous work. Quality measurements were measured in terms of vertical bow, twist and cross-sectional geometric accuracy, and a complete method of classifying quality has been devised. The longitudinal strain profile was recorded, by the use of strain gauges attached to the strip surface at five locations. Parameter control is shown to be important in allowing consistency in section quality. At present rolling mills are constructed with large tolerances on operating conditions. By reduction of the variability in parameters, section consistency is maintained and mill down-time is reduced. Roll load, alignment and differential roll speed are all shown to affect quality, and can be used to control quality. Set-up time is reduced by improving the design of the mill so that parameter values can be measured and set, without the need for judgment by eye. Values of parameters can be guided by models of the process, although elements of experience are still unavoidable. Despite increased parameter control, section quality is variable, if only due to variability in strip material properties. Parameters must therefore be changed during rolling. Ideally this can take place by closed-loop feedback control. Future work lies in overcoming the problems connected with this control.

Examination variability in short-wavelength automated perimetry

The study evaluated sources of within- and between-subject variability in standard white-on-white (W-W) perimetry and short-wavelength automated perimetry (SWAP). The Influence of staircase strategy on the fatigue effect in W-W perimetry was investigated for a 4 dB single step, single reversal strategy; a variable step size, single reversal dynamic strategy; and the standard 4-2 dB double reversal strategy. The fatigue effect increased as the duration of the examination Increased and was greatest in the second eye for all strategies. The fatigue effect was lowest for the 4dB strategy, which exhibited the shortest examination time and was greatest for the 4-2 dB strategy, which exhibited the longest examination time. Staircase efficiency was lowest for the 4 dB strategy and highest for the dynamic strategy which thus offers a reduced examination time and low inter-subject variability. The normal between-subject variability of SWAP was determined for the standard 4-2 dB double reversal strategy and the 3 dB single reversal FASTPAC strategy and compared to that of W-W perimetry, The decrease in sensitivity with Increase in age was greatest for SWAP. The between-subject variability of SWAP was greater than W-W perimetry. Correction for the Influence of ocular media absorption reduced the between-subject variability of SWAP, The FASTPAC strategy yielded the lowest between-subject variability In SWAP, but the greatest between-subject variability In WoW perimetry. The greater between-subject variability of SWAP has profound Implications for the delineation of visual field abnormality, The fatigue effect for the Full Threshold strategy in SWAP was evaluated with conventional opaque, and translucent occlusion of the fellow eye. SWAP exhibited a greater fatigue effect than W-W perimetry. Translucent occlusion reduced the between-subject variability of W-W perimetry but Increased the between-subject variability of SWAP. The elevation of sensitivity was greater with translucent occlusion which has implications for the statistical analysis of W-W perimetry and SWAP. The influence of age-related cataract extraction and IOL implantation upon the visual field derived by WoW perimetry and SWAP was determined. Cataract yielded a general reduction In sensitivity which was preferentially greater in SWAP, even after the correction of SWAP for the attenuation of the stimulus by the ocular media. There was no correlation between either backward or forward light scatter and the magnitude of the attenuation of W-W or SWAP sensitivity. The post-operative mean deviation in SWAP was positive and has ramifications for the statistical Interpretation of SWAP. Short-wavelength-sensitive pathway isolation was assessed as a function of stimulus eccentricity using the two-colour Increment threshold method. At least 15 dB of SWS pathway Isolation was achieved for 440 nm, 450 nm and 460 nm stimuli at a background luminance of 100 cdm-2, There was a slight decrease In SWS pathway Isolation for all stimulus wavelengths with increasing eccentricity which was not of clinical significance. Adopting a 450 nm stimulus may reduce between-subject variability In SWAP due to a reduction In ocular media absorption and macular pigment absorption.

An analysis of progressive addition spectacles lens design by the use of interferometry

Progressive addition spectacle lenses (PALs) have now become the method of choice for many presbyopic individuals to alleviate the visual problems of middle-age. Such lenses are difficult to assess and characterise because of their lack of discrete geographical locators of their key features. A review of the literature (mostly patents) describing the different designs of these lenses indicates the range of approaches to solving the visual problem of presbyopia. However, very little is published about the comparative optical performance of these lenses. A method is described here based on interferometry for the assessment of PALs, with a comparison of measurements made on an automatic focimeter. The relative merits of these techniques are discussed. Although the measurements are comparable, it is considered that the interferometry method is more readily automated, and would be ultimately capable of producing a more rapid result.

Understanding U.S. regional linguistic variation with Twitter data analysis

We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.

Self-training from labeled features for sentiment analysis

Sentiment analysis concerns about automatically identifying sentiment or opinion expressed in a given piece of text. Most prior work either use prior lexical knowledge defined as sentiment polarity of words or view the task as a text classification problem and rely on labeled corpora to train a sentiment classifier. While lexicon-based approaches do not adapt well to different domains, corpus-based approaches require expensive manual annotation effort. In this paper, we propose a novel framework where an initial classifier is learned by incorporating prior information extracted from an existing sentiment lexicon with preferences on expectations of sentiment labels of those lexicon words being expressed using generalized expectation criteria. Documents classified with high confidence are then used as pseudo-labeled examples for automatical domain-specific feature acquisition. The word-class distributions of such self-learned features are estimated from the pseudo-labeled examples and are used to train another classifier by constraining the model's predictions on unlabeled instances. Experiments on both the movie-review data and the multi-domain sentiment dataset show that our approach attains comparable or better performance than existing weakly-supervised sentiment classification methods despite using no labeled documents.

To cut a long story short:an analysis of formulaic sequences in short written narratives and their potential as markers of authorship

Previous research into formulaic language has focussed on specialised groups of people (e.g. L1 acquisition by infants and adult L2 acquisition) with ordinary adult native speakers of English receiving less attention. Additionally, whilst some features of formulaic language have been used as evidence of authorship (e.g. the Unabomber’s use of you can’t eat your cake and have it too) there has been no systematic investigation into this as a potential marker of authorship. This thesis reports the first full-scale study into the use of formulaic sequences by individual authors. The theory of formulaic language hypothesises that formulaic sequences contained in the mental lexicon are shaped by experience combined with what each individual has found to be communicatively effective. Each author’s repertoire of formulaic sequences should therefore differ. To test this assertion, three automated approaches to the identification of formulaic sequences are tested on a specially constructed corpus containing 100 short narratives. The first approach explores a limited subset of formulaic sequences using recurrence across a series of texts as the criterion for identification. The second approach focuses on a word which frequently occurs as part of formulaic sequences and also investigates alternative non-formulaic realisations of the same semantic content. Finally, a reference list approach is used. Whilst claiming authority for any reference list can be difficult, the proposed method utilises internet examples derived from lists prepared by others, a procedure which, it is argued, is akin to asking large groups of judges to reach consensus about what is formulaic. The empirical evidence supports the notion that formulaic sequences have potential as a marker of authorship since in some cases a Questioned Document was correctly attributed. Although this marker of authorship is not universally applicable, it does promise to become a viable new tool in the forensic linguist’s tool-kit.

Joint sentiment/topic model for sentiment analysis

Sentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework based on Latent Dirichlet Allocation (LDA), called joint sentiment/topic model (JST), which detects sentiment and topic simultaneously from text. Unlike other machine learning approaches to sentiment classification which often require labeled corpora for classifier training, the proposed JST model is fully unsupervised. The model has been evaluated on the movie review dataset to classify the review sentiment polarity and minimum prior information have also been explored to further improve the sentiment classification accuracy. Preliminary experiments have shown promising results achieved by JST.