A Dependency Parsing Approach to Biomedical Text Mining

Biomedical research is currently facing a new type of challenge: an excess of information, both in terms of raw data from experiments and in the number of scientific publications describing their results. Mirroring the focus on data mining techniques to address the issues of structured data, there has recently been great interest in the development and application of text mining techniques to make more effective use of the knowledge contained in biomedical scientific publications, accessible only in the form of natural human language. This thesis describes research done in the broader scope of projects aiming to develop methods, tools and techniques for text mining tasks in general and for the biomedical domain in particular. The work described here involves more specifically the goal of extracting information from statements concerning relations of biomedical entities, such as protein-protein interactions. The approach taken is one using full parsing—syntactic analysis of the entire structure of sentences—and machine learning, aiming to develop reliable methods that can further be generalized to apply also to other domains. The five papers at the core of this thesis describe research on a number of distinct but related topics in text mining. In the first of these studies, we assessed the applicability of two popular general English parsers to biomedical text mining and, finding their performance limited, identified several specific challenges to accurate parsing of domain text. In a follow-up study focusing on parsing issues related to specialized domain terminology, we evaluated three lexical adaptation methods. We found that the accurate resolution of unknown words can considerably improve parsing performance and introduced a domain-adapted parser that reduced the error rate of theoriginal by 10% while also roughly halving parsing time. To establish the relative merits of parsers that differ in the applied formalisms and the representation given to their syntactic analyses, we have also developed evaluation methodology, considering different approaches to establishing comparable dependency-based evaluation results. We introduced a methodology for creating highly accurate conversions between different parse representations, demonstrating the feasibility of unification of idiverse syntactic schemes under a shared, application-oriented representation. In addition to allowing formalism-neutral evaluation, we argue that such unification can also increase the value of parsers for domain text mining. As a further step in this direction, we analysed the characteristics of publicly available biomedical corpora annotated for protein-protein interactions and created tools for converting them into a shared form, thus contributing also to the unification of text mining resources. The introduced unified corpora allowed us to perform a task-oriented comparative evaluation of biomedical text mining corpora. This evaluation established clear limits on the comparability of results for text mining methods evaluated on different resources, prompting further efforts toward standardization. To support this and other research, we have also designed and annotated BioInfer, the first domain corpus of its size combining annotation of syntax and biomedical entities with a detailed annotation of their relationships. The corpus represents a major design and development effort of the research group, with manual annotation that identifies over 6000 entities, 2500 relationships and 28,000 syntactic dependencies in 1100 sentences. In addition to combining these key annotations for a single set of sentences, BioInfer was also the first domain resource to introduce a representation of entity relations that is supported by ontologies and able to capture complex, structured relationships. Part I of this thesis presents a summary of this research in the broader context of a text mining system, and Part II contains reprints of the five included publications.

Construction of an index of information from clinical practice in Radiology and Imaging Diagnosis based on text mining and thesaurus

Objective To construct a Portuguese language index of information on the practice of diagnostic radiology in order to improve the standardization of the medical language and terminology. Materials and Methods A total of 61,461 definitive reports were collected from the database of the Radiology Information System at Hospital das Clínicas – Faculdade de Medicina de Ribeirão Preto (RIS/HCFMRP) as follows: 30,000 chest x-ray reports; 27,000 mammography reports; and 4,461 thyroid ultrasonography reports. The text mining technique was applied for the selection of terms, and the ANSI/NISO Z39.19-2005 standard was utilized to construct the index based on a thesaurus structure. The system was created in *html. Results The text mining resulted in a set of 358,236 (n = 100%) words. Out of this total, 76,347 (n = 21%) terms were selected to form the index. Such terms refer to anatomical pathology description, imaging techniques, equipment, type of study and some other composite terms. The index system was developed with 78,538 *html web pages. Conclusion The utilization of text mining on a radiological reports database has allowed the construction of a lexical system in Portuguese language consistent with the clinical practice in Radiology.

Text i context. El concurs de cinema amateur «JULIUS» (1987-1996)

El «Julius» és un concurs de cinema amateur que fonamenta la seva singularitat en el fet de partir d’un text literari prefixat del qual els participants han de fer una adaptació audiovisual. En aquest article s’estudia la primera època del concurs: el seu origen, les diverses edicions en què es dugué a terme, les incidències que s’hi produïren..., i el context social i cultural que va contribuir a fer-ne un concurs amb unes característiques úniques que es concretaren en l’anomenat «esperit Julius», sorneguer, llibertari i surrealista.

Jane Eyre: del text a la pantalla : Un estudi comparatiu entre l'obra de Charlotte Brontë i l'adaptació cinematogràfica de Cary Fukunaga

Treball de fi de màster que estudia comparativament les relacions entre la novel·la "Jane Eyre" de Charlotte Brontë i l'adaptació cinematogràfica de la mateixa realitzada pel director Cary Fukunaga.

Les Sentències catòliques del diví poeta Dant (1545) d’en Jaume Ferrer de Blanes: edició crítica del text

Procurador reial i nobiliari, cosmògraf, joier, lapidari, mercader i escriptor, i al capdavall, un ciutadà català honrat, en Ferrer (Vidreres, ~1445 – Blanes, 1529) va marxar de ben jove, primer, a la cort de Nàpols, al servei del rei en Ferran I, i després a la cort de Sicília, al servei de la reina na Joana de Sicília. Acabada aquesta peripècia italiana va tornar a Blanes al servei del vescomte de Cabrera i de Bas fins que va morir a la mateixa vila al 1529. Un seu criat, disset anys més tard, va editar uns papers esparsos que havia trobat a can Ferrer, les (sic) Sentèncias cathòlicas del diví poeta Dant florentí, compilades per lo prudentíssim mossèn Jaume Ferrer de Blanes, incloent-hi tres parts. La primera, Conclusions, és un sumari destinat a mostrar (sic) «Entre totas las cosas necessàries a l’home per aconseguir lo seu fi y beatitut eterna principalment són tres»; la segona, Meditació, és una reflexió a fi d’il•luminar els misteris sobre la passió i mort de Jesucrist a (sic) «lo santíssim loch de Calvari»; la tercera, Letras, és un conjunt de dotze documents, entre cartes i d’altres textos, «fetas a mossèn Jaume Ferrer, respostes e regles per ell ordenades en cosmographia y en art de navegar». En Ferrer, home de grans recursos, fa un recorregut per tots els coneixements que havia acumulat al llarg de la seva vida, de Dant Alighieri a Ptolemeu i del marquès de Santillana a Albert Gran o a Aristòtil, fent servir fragments de la Commedia, dels Proverbios, de la Bíblia i de moltes altres autoritats científiques i filosòfiques, en català, italià, espanyol, llatí i, també, set mots en arameu

Proposta d’un text articulat sobre teoria general del contracte per al Llibre sisè del Codi Civil de Catalunya

El treball que es presenta conté un text articulat sobre la part de teoria general del contracte (arts. 612-1 i següents) del llibre sisè del Codi Civil de Catalunya. El procés de codificació civil que es viu a Catalunya justifica aquest treball, que podria ser útil per a elaboració del llibre sisè del CCCat dedicat a les obligacions i els contractes. El treball consta d’una proposta de text articulat, amb el seus respectius comentaris a cada article. Es tracta del capítol segon del títol primer del llibre sisè, i es divideix en les següents seccions: 1) El contracte, els seus elements essencials, i la seva eficàcia; 2) La formació del contracte; 3) La interpretació del contracte; i 4) La ineficàcia del contracte, que inclou l’anàlisi dels vicis del consentiment. El treball ha pres com a referència les principals propostes d’harmonització del dret contractual (Principis Unidroit [PICC], Principis de Dret Contractual Europeu [PECL], Marc Comú de Referència [DCFR], i l’Instrument Opcional sobre Compravenda Europea [CESL] i la regulació dels codis més moderns (entre ells, el del Quebec, l’Holandès, el Portuguès o l’Italià) i les seves propostes de reforma (el projecte Terrè a França, i la Propuesta de Modificación del Código Civil Español en materia de obligaciones y contratos). En la proposta presentada s’incorporen institucions no regulades en el Codi civil espanyol actualment vigent a Catalunya en la seva condició de dret supletori, i s’omplen algunes llacunes d’aquest cos legal. Es poden citar, entre elles, les clàusules abusives dels contractes, el canvi en les circumstàncies essencials del contracte, el contracte per a persona per designar, la responsabilitat per culpa in contrahendo, les cartes d’intencions, el règim de l’oferta i l’acceptació del contracte, els contractes preparatoris, els drets de preferència, la possibilitat d’anul·lació del contracte per concessió d’un avantatge injust a alguna de les parts, i el règim dels contractes en frau de creditors.

Machine Learning and Clinical Text. Supporting Health Information Flow

Fluent health information flow is critical for clinical decision-making. However, a considerable part of this information is free-form text and inabilities to utilize it create risks to patient safety and cost-­effective hospital administration. Methods for automated processing of clinical text are emerging. The aim in this doctoral dissertation is to study machine learning and clinical text in order to support health information flow.First, by analyzing the content of authentic patient records, the aim is to specify clinical needs in order to guide the development of machine learning applications.The contributions are a model of the ideal information flow,a model of the problems and challenges in reality, and a road map for the technology development. Second, by developing applications for practical cases,the aim is to concretize ways to support health information flow. Altogether five machine learning applications for three practical cases are described: The first two applications are binary classification and regression related to the practical case of topic labeling and relevance ranking.The third and fourth application are supervised and unsupervised multi-class classification for the practical case of topic segmentation and labeling.These four applications are tested with Finnish intensive care patient records.The fifth application is multi-label classification for the practical task of diagnosis coding. It is tested with English radiology reports.The performance of all these applications is promising. Third, the aim is to study how the quality of machine learning applications can be reliably evaluated.The associations between performance evaluation measures and methods are addressed,and a new hold-out method is introduced.This method contributes not only to processing time but also to the evaluation diversity and quality. The main conclusion is that developing machine learning applications for text requires interdisciplinary, international collaboration. Practical cases are very different, and hence the development must begin from genuine user needs and domain expertise. The technological expertise must cover linguistics,machine learning, and information systems. Finally, the methods must be evaluated both statistically and through authentic user-feedback.

Polarizabilidades e primeira hiperpolarizabilidades elétricas dipolares de ésteres E-4-amino-trans-1,3-butadienil-(1',2'-di-hidroxibenzeno) de boro, alumínio e gálio

Static electric dipole polarizabilities and first hyperpolarizabilites have been calculated for the title molecules and their 3' and 4'-nitro derivatives at ab-initio Hartree- Fock/6-31G(d, p) level. The influence of the pivotal p vacant 3A elements (B, Al or Ga) substitution on the electrical properties of these molecules is detailed. The axial vector components of the first hyperpolarizabilities β(0) of the push-pull 4'-nitro derivatives, -18.2×10-32 esu (B), -21.1×10-32 esu (Al) and -20.8×10-32 esu (Ga) are calculated to be as much as fourfold larger then that calculated for the p-nitroaniline, a reference organic molecule for comparison for this type of molecular property.